N Neurarch Try it See it Changes Bot Pricing API Open app

Models / Changes

The model at that id is not the model you tested.

307 of the 652 open-weight models with readable history (606 tracked) changed a tracked key after their first upload; 137 changed a structural one, 74 of them more than a week after release. Each row is one commit that changed a model's config, tokenizer, chat template, generation defaults or weights, with what that change does.

Models tracked
606
With history
652
Changes
741
Structural
210
Tokenizer / template
454
Format-only
12

-46 of the 606 tracked models have no history yet: none of the tracked files (GGUF-only repos, adapters) or files the tracker cannot read (gated). By most consequential class: 210 structural, 242 tokenizer, 212 template, 41 generation-defaults, 0 weights-only, 24 metadata, 12 format-only. 12 rows are format-only re-saves and 2 more carry a format-only key next to a real one. Template changes rendered on the fixed conversations: 149 rendering-changed, 66 cosmetic, 17 the renderer could not run, 0 not rendered yet. 106 rows carry a safety-relevant config change. 392 of the 741 landed more than a week after the model's first commit, so they are not release-day fixes. History reaches back to 2019-02-18; 5 of the changes were caught by a daily snapshot rather than recovered from git. Last read 2026-11-11.

DateModelClassWhat changed, and what it does
2026-10-28XiaomiMiMo/MiMo-V2.5format-onlyformat-only re-save, the parameter total the Hub reports moved, with no weight shard recorded as changing; nothing it computes, tokenises or generates changed (2026-10-28). Open in app
2026-10-26kindlingai/glm-5.3-exlr8-k2-k3-k4format-onlyformat-only re-save, safetensors files the index does not load were added or changed; every shard a loader reads is identical; nothing it computes, tokenises or generates changed (2026-10-26). Open in app
2026-10-26MiniMaxAI/MiniMax-M3-MXFP8format-onlyformat-only re-save, the parameter total the Hub reports moved, with no weight shard recorded as changing; nothing it computes, tokenises or generates changed (2026-10-26). Open in app
2026-10-26MiniMaxAI/MiniMax-M2.5format-onlyformat-only re-save, the parameter total the Hub reports moved, with no weight shard recorded as changing; nothing it computes, tokenises or generates changed (2026-10-26). Open in app
2026-10-25ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUFtemplate unrenderedthe chat template text changed; the renderer could not run one of the two versions, so whether rendered prompts changed is not known (2026-10-25). Open in app
2026-10-20ornith-ai/Ornith-1.5-397B-NVFP4format-onlyformat-only re-save, safetensors files the index does not load were added or changed; every shard a loader reads is identical; nothing it computes, tokenises or generates changed (2026-10-20). Open in app
2026-10-16ornith-ai/Ornith-1.5-122Btemplate rendering-changedthe chat template changed and renders differently (multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-10-16). Open in app
2026-10-16ornith-ai/Ornith-1.5-122Btemplate rendering-changedthe chat template changed and renders differently (multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-10-16). Open in app
2026-10-16ornith-ai/Ornith-1.5-122Btemplate rendering-changedthe chat template changed and renders differently (multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-10-16). Open in app
2026-10-15zai-org/GLM-5.3-Flashtemplate unrenderedthe chat template text changed; the renderer could not run one of the two versions, so whether rendered prompts changed is not known (2026-10-15). Open in app
2026-10-14zai-org/GLM-5.3template unrenderedthe chat template text changed; the renderer could not run one of the two versions, so whether rendered prompts changed is not known (2026-10-14). Open in app
2026-10-14baidu/Unlimited-OCRstructural templatemodel_type "unlimited-ocr" to "unlimited_ocr", the same name respelt with underscores rather than a different architecture; a chat template was added; apply_chat_template now formats prompts that it previously refused or formatted by default (2026-10-14). Open in app
2026-10-05unsloth/gpt-oss-20b-BF16tokenizer template rendering-changed default system promptEOS stop list [200002,199999] to [200002,199999,200012]; generation now also stops on 200012, and still stops on every token it stopped on before; the chat template changed and renders differently (system+user, multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-10-05).default system prompt: With no system message, the text rendered before the user's message changed: "...uded for every message. Calls to these tools must go to the commentary channel: 'f..." became "...uded for every message. user". Open in app
2026-10-02jialinyyzz/humanizerstructuralhidden size 2560 to 3840, MLP width 10240 to 15360, attention heads 8 to 16, layer count 42 to 48, KV heads 2 to 8; derived parameters 4.64B to 11.79B (+7.14B, +14.29 GB of bf16 weights); context window 131072 to 262144 tokens (2026-10-02). Open in app
2026-10-01deepseek-ai/DeepSeek-V4.1-Flashtemplatea chat template was added; apply_chat_template now formats prompts that it previously refused or formatted by default (2026-10-01). Open in app
2026-09-29openbmb/MiniCPM5-2Btemplate unrenderedthe chat template text changed; the renderer could not run one of the two versions, so whether rendered prompts changed is not known (2026-09-29). Open in app
2026-09-27Qdrant/all-MiniLM-L6-v2-onnxtokenizertokenizer model_max_length 512 to 256; truncation defaults change (2026-09-27). Open in app
2026-09-14biohub/ESMC-6Bstructural tokenizerEOS declared as 2 (was unset); generation that relied on the library default now stops on this token; config.json BOS declared as 0 (was unset); head dim 64, MLP width 6912, attention heads 40, layer count 80, KV heads 40 declared (each was unset, so the library default for the class applied) (2026-09-14). Open in app
2026-09-05CMSManhattan/JiRackUltra_1btemplate rendering-changed generation prefixthe chat template changed and renders differently (system+user, multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-09-05).generation prefix: With add_generation_prompt, what follows the user's message changed from "<|Assistant|><think>\n" to "<|Assistant|><think>\n\n</think>\n\n". Open in app
2026-09-04zai-org/GLM-5.3-Flashtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-09-04). Open in app
2026-09-04zai-org/GLM-5.3template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-09-04). Open in app
2026-09-01farbodtavakkoli/OTel-2.0-LLM-31B-ITstructural tokenizer template rendering-changed generation prefixEOS stop list 106 to [1,106]; generation now also stops on 1, and still stops on every token it stopped on before; derived parameters 30.15B to 30.56B (+418.7M) only because the reconstruction follows the class name; no size key changed; architectures declared as ["Gemma4ForConditionalGeneration"] (was unset) (2026-09-01).generation prefix: With add_generation_prompt, what follows the user's message changed from "<turn|>\n<|turn>model\n<|channel>thought\n<channel|>" to "<turn|>\n<|turn>model\n". Open in app
2026-08-29ornith-ai/Ornith-1.5-397B-NVFP4structuralquantization_config changed; the stored format of the weights is different (2026-08-29). Open in app
2026-08-29unsloth/GLM-5.3-GGUFtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-08-29). Open in app
2026-08-28RadixArk/Qwen3.8-27B-DSparkstructural tokenizerEOS changed from 248046 to 248044; anything fine-tuned or served against the old value stops at a different token; config.json BOS 248044 removed; MLP width 10240 to 17408, attention heads 40 to 32 (2026-08-28). Open in app
2026-08-26zai-org/GLM-5.3-Flashtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-08-26). Open in app
2026-08-26zai-org/GLM-5.3-Flashtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-08-26). Open in app
2026-08-24ai-sage/Giga-Embeddings-instruct-480M-0826structuralcontext window 32768 to 8192 tokens (2026-08-24). Open in app
2026-08-23OBLITERATUS/Qwen3.8-27B-OBLITERATEDtemplate rendering-changed generation prefixthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-08-23).generation prefix: With add_generation_prompt, what follows the user's message changed from "<|im_end|><|im_start|>assistant\n<think>\n\n</think>" to "<|im_end|><|im_start|>assistant<think>\n\n</think>". Open in app
2026-08-23OBLITERATUS/Qwen3.8-27B-OBLITERATEDtokenizerconfig.json eos_token_id 248044 to 248046, but generation_config.json still declares [248046], which generate() reads first, so default generation stops on the same tokens; only code that reads config.eos_token_id directly sees the new value; config.json pad_token_id unset to 248044; the tokenizer's pad token, which training pads with, did not change (2026-08-23). Open in app
2026-08-23OBLITERATUS/Qwen3.8-27B-OBLITERATEDtokenizerEOS stop list [248046,248044] to [248046]; generation no longer stops on 248044 and runs past it (2026-08-23). Open in app
2026-08-22OBLITERATUS/Qwen3.8-27B-OBLITERATEDstructural tokenizer template rendering-changed tool block generation prefixderived parameters 26.79B to 26.79B (+7.0M) only because the reconstruction follows the class name; no size key changed; architectures ["Qwen3_5ForCausalLM"] to ["Qwen3_5ForConditionalGeneration"]; a different class is instantiated from the same id; the chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-08-22).tool block: A tool list passed to the template reached the prompt before and is dropped now.generation prefix: With add_generation_prompt, what follows the user's message changed from "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n" to "<|im_end|><|im_start|>assistant\n<think>\n\n</think>". Open in app
2026-08-22OBLITERATUS/Qwen3.8-27B-OBLITERATEDstructural tokenizerderived parameters 26.79B to 26.79B (-7.0M) only because the reconstruction follows the class name; no size key changed; architectures ["Qwen3_5ForConditionalGeneration"] to ["Qwen3_5ForCausalLM"]; a different class is instantiated from the same id; add_bos_token false to unset; encoding the same text yields different ids (2026-08-22). Open in app
2026-08-21bloomer010/Ling-3.0-tiny-GGUFtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-08-21). Open in app
2026-08-20OBLITERATUS/Qwen3.8-27B-OBLITERATEDtemplate rendering-changed default system prompt generation prefixthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-08-20).default system prompt: With no system message, the text rendered before the user's message removed: "system Reasoning effort is set to xhigh. Please think carefully through the task, val..." became "user".generation prefix: With add_generation_prompt, what follows the user's message changed from "<|im_end|>\n<|im_start|>assistant\n<think>\n" to "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n". Open in app
2026-08-19OBLITERATUS/Qwen3.8-27B-OBLITERATEDstructural tokenizer templatederived parameters 26.79B to 26.79B (+7.0M) only because the reconstruction follows the class name; no size key changed; architectures ["Qwen3_5ForCausalLM"] to ["Qwen3_5ForConditionalGeneration"]; a different class is instantiated from the same id; a chat template was added; apply_chat_template now formats prompts that it previously refused or formatted by default (2026-08-19). Open in app
2026-08-19ornith-ai/Ornith-1.5-397B-FP8structuralquantization_config changed; the stored format of the weights is different (2026-08-19). Open in app
2026-08-19ornith-ai/Ornith-1.5-35B-A3B-FP8structuralquantization_config changed; the stored format of the weights is different (2026-08-19). Open in app
2026-08-19ornith-ai/Ornith-1.5-35B-A3Btokenizeradd_bos_token unset to false; encoding the same text yields different ids (2026-08-19). Open in app
2026-08-14ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUFtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-08-14). Open in app
2026-08-13webAI-Official/TwIL-LM3tokenizertokenizer model_max_length 131072 to 65536; truncation defaults change; tokenizer_class unset to "PreTrainedTokenizerFast" (2026-08-13). Open in app
2026-08-13Qwen/Qwen3.8-27B-FP8generation-defaultsgeneration defaults changed (temperature 0.6 to 1); a call that does not pass these explicitly now generates differently (2026-08-13). Open in app
2026-08-13Qwen/Qwen3.8-27B-FP8template rendering-changed default system promptthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-08-13).default system prompt: With no system message, the text rendered before the user's message added: "user" became "system Reasoning effort is set to xhigh. Please think carefully through the task, val...". Open in app
2026-08-13Qwen/Qwen3.8-27Bgeneration-defaultsgeneration defaults changed (temperature 0.6 to 1); a call that does not pass these explicitly now generates differently (2026-08-13). Open in app
2026-08-13Qwen/Qwen3.8-27Btemplate rendering-changed default system promptthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-08-13).default system prompt: With no system message, the text rendered before the user's message added: "user" became "system Reasoning effort is set to xhigh. Please think carefully through the task, val...". Open in app
2026-08-13Qwen/Qwen3.8-27B-FP8tokenizertokenizer model_max_length 131072 to 262144; truncation defaults change (2026-08-13). Open in app
2026-08-13Qwen/Qwen3.8-27Btokenizertokenizer model_max_length 131072 to 262144; truncation defaults change (2026-08-13). Open in app
2026-08-10nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4structuralcontext window 262144 to 1048576 tokens (2026-08-10). Open in app
2026-08-05nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-08-05). Open in app
2026-08-05nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-08-05). Open in app
2026-08-03farbodtavakkoli/OTel-2.0-LLM-31B-ITtokenizerEOS changed from "<eos>" to "<turn|>"; anything fine-tuned or served against the old value stops at a different token (2026-08-03). Open in app
2026-08-01poolside/Laguna-S-2.1-NVFP4structuralcontext window 262144 to 1048576 tokens; quantization_config changed; the stored format of the weights is different (2026-08-01). Open in app
2026-07-31RadixArk/Kimi-K3-DSparkstructuralrope_scaling added ({"factor":16,"original_max_position_embeddings":65536,"ro...); positions are now scaled (2026-07-31). Open in app
2026-07-29poolside/Laguna-XS-2.1generation-defaultsgeneration defaults changed (top_k unset to 20); a call that does not pass these explicitly now generates differently (2026-07-29). Open in app
2026-07-25farbodtavakkoli/OTel-2.0-LLM-31B-ITgeneration-defaultsgeneration_config.json was removed; whatever defaults it set now come from the library (2026-07-25). Open in app
2026-07-24farbodtavakkoli/OTel-2.0-LLM-31B-ITstructural tokenizer template cosmeticconfig.json eos_token_id [1,106] to 1, but generation_config.json still declares [1,106,50], which generate() reads first, so default generation stops on the same tokens; only code that reads config.eos_token_id directly sees the new value; derived parameters 30.56B to 30.15B (-418.7M) only because the reconstruction follows the class name; no size key changed; architectures ["Gemma4ForConditionalGeneration"] removed; the class is now inferred from model_type (2026-07-24). Open in app
2026-07-24k-chirkunov/gemma4-e4b-claims-comparisontokenizer template cosmeticpad token "<eos>" to "<pad>"; batched training masks a different id; the chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-07-24). Open in app
2026-07-23ibm-research/MoLFormer-XL-both-10pcttokenizer format-onlyEOS declared as "<eos>" (was unset); generation that relied on the library default now stops on this token; BOS declared as "<bos>" (was unset); tokenizer_class "MolformerTokenizer" to "PreTrainedTokenizerFast" (2026-07-23). Open in app
2026-07-23AnkitAI/Parable-Qwen3-4B-Claude-Fable-5-GGUFtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-07-23). Open in app
2026-07-22poolside/Laguna-S-2.1-NVFP4structuralquantization_config changed; the stored format of the weights is different (2026-07-22). Open in app
2026-07-21poolside/Laguna-S-2.1-NVFP4template generation-defaults rendering-changed generation prefixthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering; generation defaults changed (max_new_tokens 32768 to unset); a call that does not pass these explicitly now generates differently (2026-07-21).generation prefix: With add_generation_prompt, what follows the user's message changed from "</user>\n<assistant></think>" to "</user>\n<assistant><think>". Open in app
2026-07-21poolside/Laguna-S-2.1template generation-defaults rendering-changed generation prefixthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering; generation defaults changed (max_new_tokens 32768 to unset); a call that does not pass these explicitly now generates differently (2026-07-21).generation prefix: With add_generation_prompt, what follows the user's message changed from "</user>\n<assistant></think>" to "</user>\n<assistant><think>". Open in app
2026-07-21poolside/Laguna-S-2.1template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-07-21). Open in app
2026-07-20tencent/Hy3declared dtype unset to "bfloat16" (2026-07-20). Open in app
2026-07-18unsloth/Ornith-1.0-9B-GGUFtemplate rendering-changedthe chat template changed and renders differently (multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-07-18). Open in app
2026-07-15thinkingmachines/Inklingtemplatea chat template was added; apply_chat_template now formats prompts that it previously refused or formatted by default (2026-07-15). Open in app
2026-07-15google/gemma-4-31B-ittemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-07-15). Open in app
2026-07-15google/gemma-4-26B-A4B-ittemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-07-15). Open in app
2026-07-14microsoft/phi-4tokenizerEOS stop list 100265 to [100257,100265]; generation now also stops on 100257, and still stops on every token it stopped on before (2026-07-14). Open in app
2026-07-13ibm-granite/granite-vision-4.1-4bstructuralvocab_size changed from 100353 to 100352; the embedding and output head change shape, so adapters and merges made against the old vocabulary no longer load cleanly; derived parameters 3.32B to 3.32B (-2.6K, -0.00 GB of bf16 weights) (2026-07-13). Open in app
2026-07-12ibm-granite/granite-vision-4.1-4btokenizertokenizer_class "GPT2Tokenizer" to "PreTrainedTokenizerFast" (2026-07-12). Open in app
2026-07-08OpenMOSS-Team/MOSS-Transcribe-Diarizetokenizeradd_bos_token false to unset; encoding the same text yields different ids (2026-07-08). Open in app
2026-07-07poolside/Laguna-XS-2.1template rendering-changed default system prompt generation prefixthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-07-07).default system prompt: With no system message, the text rendered before the user's message added: "" became "You are a helpful, conversationally-fluent assistant made by Poolside. You are here t...".generation prefix: With add_generation_prompt, what follows the user's message changed from "\n</user>\n<assistant>\n</think>" to "</user>\n<assistant></think>". Open in app
2026-07-06OpenMOSS-Team/MOSS-Transcribe-Diarizestructural context window 40960 to 131072 tokens; declared dtype unset to "bfloat16" (2026-07-06). Open in app
2026-07-05tencent/Hy3template unrenderedthe chat template text changed; the renderer could not run one of the two versions, so whether rendered prompts changed is not known (2026-07-05). Open in app
2026-07-03Bahushruth/Qwen3.6-35B-A3B-abliterated-v4structuralarchitectures ["Qwen3_5MoeForConditionalGeneration"] to ["Qwen3_5MoeForCausalLM"]; a different class is instantiated from the same id (2026-07-03). Open in app
2026-07-03Bahushruth/Qwen3.6-35B-A3B-abliterated-v4structuralarchitectures ["Qwen3_5MoeForCausalLM"] to ["Qwen3_5MoeForConditionalGeneration"]; a different class is instantiated from the same id (2026-07-03). Open in app
2026-06-30nvidia/Qwen3.6-27B-NVFP4structuralquantization_config changed; the stored format of the weights is different (2026-06-30). Open in app
2026-06-27google/tipsv2-so400m14structural tokenizerhidden size 1152, MLP width 4304, attention heads 16, layer count 27 declared (each was unset, so the library default for the class applied); context window unset to 64 tokens; config.json pad_token_id unset to 0; the tokenizer's pad token, which training pads with, did not change (2026-06-27). Open in app
2026-06-27google/tipsv2-b14structural tokenizerhidden size 768, MLP width 3072, attention heads 12, layer count 12 declared (each was unset, so the library default for the class applied); context window unset to 64 tokens; config.json pad_token_id unset to 0; the tokenizer's pad token, which training pads with, did not change (2026-06-27). Open in app
2026-06-25ornith-ai/Ornith-1.0-397B-FP8template rendering-changedthe chat template changed and renders differently (multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-06-25). Open in app
2026-06-24nvidia/MiniMax-M3-NVFP4tokenizerEOS declared as "[e~[" (was unset); generation that relied on the library default now stops on this token; BOS declared as "]~b]" (was unset); pad token unset to "]!p~["; batched training masks a different id (2026-06-24). Open in app
2026-06-19z-lab/Qwen3.6-35B-A3B-DFlashstructural tokenizerEOS changed from 248046 to 248044; anything fine-tuned or served against the old value stops at a different token; layer count 8 to 6, KV heads 4 to 8; derived parameters 1.47B to 1.37B (-100.7M, -0.20 GB of bf16 weights) (2026-06-19). Open in app
2026-06-15moonshotai/Kimi-K2.7-Codetemplate generation-defaults cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; generation defaults changed (temperature unset to 1, top_p unset to 0.95); a call that does not pass these explicitly now generates differently (2026-06-15). Open in app
2026-05-27poolside/Laguna-XS.2generation-defaultsgeneration defaults changed (max_new_tokens 2048 to 4096, min_p unset to 0, temperature 0.7 to 1, top_p 0.9 to 1); a call that does not pass these explicitly now generates differently (2026-05-27). Open in app
2026-05-26poolside/Laguna-XS.2structuralcontext window 131072 to 262144 tokens (2026-05-26). Open in app
2026-05-18google/gemma-4-31B-ittemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-05-18). Open in app
2026-05-18google/gemma-4-26B-A4B-ittemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-05-18). Open in app
2026-05-12moonshotai/Kimi-K2.6format-onlyformat-only re-save, tokenizer class renamed between its Fast and plain spelling (one class per model since transformers v5); nothing it computes, tokenises or generates changed (2026-05-12). Open in app
2026-05-11moonshotai/Kimi-K2.6format-onlyformat-only re-save, tokenizer class renamed between its Fast and plain spelling (one class per model since transformers v5); nothing it computes, tokenises or generates changed (2026-05-11). Open in app
2026-05-08XiaomiMiMo/MiMo-V2.5template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-05-08). Open in app
2026-05-07XiaomiMiMo/MiMo-V2.5tokenizerEOS changed from [151643,151645,1561672] to [151643,151645,151672]; anything fine-tuned or served against the old value stops at a different token (2026-05-07). Open in app
2026-05-07nvidia/Gemma-4-26B-A4B-NVFP4template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-05-07). Open in app
2026-05-05zeroentropy/zerank-2-rerankertemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-05-05). Open in app
2026-05-01nvidia/Gemma-4-31B-IT-NVFP4template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-05-01). Open in app
2026-04-30moonshotai/Kimi-K2.5structuralquantization_config changed; the stored format of the weights is different (2026-04-30). Open in app
2026-04-30moonshotai/Kimi-K2.6structuralquantization_config changed; the stored format of the weights is different (2026-04-30). Open in app
2026-04-29sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTPtemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-29). Open in app
2026-04-28ibm-granite/granite-vision-4.1-4btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-04-28). Open in app
2026-04-28google/gemma-4-31B-ittemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-04-28). Open in app
2026-04-28google/gemma-4-26B-A4B-ittemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-04-28). Open in app
2026-04-28XiaomiMiMo/MiMo-V2.5structural template rendering-changed generation prefixcontext window 262144 to 1048576 tokens; rope_theta 5000000 to 10000000; every position embedding changes; the chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-28).generation prefix: With add_generation_prompt, what follows the user's message changed from "<|im_end|><|im_start|>assistant\n<think></think>" to "<|im_end|><|im_start|>assistant\n". Open in app
2026-04-28nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16tokenizerpad token unset to "<|im_end|>"; batched training masks a different id (2026-04-28). Open in app
2026-04-27XiaomiMiMo/MiMo-V2.5tokenizer template generation-defaults rendering-changed default system prompt tool block generation prefixEOS stop list [151643,151645] to [151643,151645,1561672]; generation now also stops on 1561672, and still stops on every token it stopped on before; the chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering; generation defaults changed (temperature unset to 1, top_p unset to 0.95); a call that does not pass these explicitly now generates differently (2026-04-27).default system prompt: With no system message, the text rendered before the user's message changed: "system You are a helpful assistant. user" became "system You are MiMo, a helpful AI assistant engineered by Xiaomi. user".tool block: A tool list passed to the template is rendered into the prompt now and was dropped before.generation prefix: With add_generation_prompt, what follows the user's message changed from "<|im_end|>\n<|im_start|>assistant\n" to "<|im_end|><|im_start|>assistant\n<think></think>". Open in app
2026-04-22Qwen/Qwen3.6-27Btokenizertokenizer model_max_length 131072 to 262144; truncation defaults change (2026-04-22). Open in app
2026-04-22Qwen/Qwen3.6-27Bgeneration-defaultsgeneration defaults changed (temperature 0.6 to 1); a call that does not pass these explicitly now generates differently (2026-04-22). Open in app
2026-04-21nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16template rendering-changed generation prefixthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-21).generation prefix: With add_generation_prompt, what follows the user's message changed from "<|im_end|>\n\n<|im_start|>assistant\n<think>\n" to "<|im_end|>\n<|im_start|>assistant\n<think>\n". Open in app
2026-04-20nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16generation-defaultsgeneration defaults changed (do_sample unset to true, max_new_tokens unset to 16384, repetition_penalty unset to 1, temperature unset to 0.6); a call that does not pass these explicitly now generates differently (2026-04-20). Open in app
2026-04-20nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16structuralarchitectures ["Nemotron_3_Nano_Omni_30B_A3B_Reasoning"] to ["NemotronH_Nano_Omni_Reasoning_V3"]; a different class is instantiated from the same id (2026-04-20). Open in app
2026-04-20MiniMaxAI/MiniMax-M2.7structuralcontext window 196608 to 204800 tokens (2026-04-20). Open in app
2026-04-18nvidia/Gemma-4-31B-IT-NVFP4template rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-18). Open in app
2026-04-17z-lab/Qwen3.6-35B-A3B-DFlashstructuralrope_scaling rewritten in a different format ({"beta_fast":32,"beta_slow":1,"factor":64,"original_max_p... to {"beta_fast":32,"beta_slow":1,"factor":64,"original_max_p...); a loader that only reads the old format rejects or ignores the new one (2026-04-17). Open in app
2026-04-16Qwen/Qwen3-Reranker-8Btemplate rendering-changed tool blockthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-16).tool block: A tool list passed to the template reached the prompt before and is dropped now. Open in app
2026-04-16Qwen/Qwen3-Reranker-4Btemplate rendering-changed tool blockthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-16).tool block: A tool list passed to the template reached the prompt before and is dropped now. Open in app
2026-04-16Qwen/Qwen3-Reranker-0.6Btemplate rendering-changed tool blockthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-16).tool block: A tool list passed to the template reached the prompt before and is dropped now. Open in app
2026-04-16zai-org/GLM-5.1template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-04-16). Open in app
2026-04-10nvidia/llama-nemotron-rerank-1b-v2format-onlyformat-only re-save, RoPE settings rewritten in the transformers v5 rope_parameters form with the same values; nothing it computes, tokenises or generates changed (2026-04-10). Open in app
2026-04-10google/gemma-4-31B-ittemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-10). Open in app
2026-04-10google/gemma-4-26B-A4B-ittemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-10). Open in app
2026-04-09MiniMaxAI/MiniMax-M2.7template rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-09).default system prompt: With no system message, the text rendered before the user's message changed: "...are a helpful assistant.[e~[ ]~b]user" became "...are a helpful assistant. Your name is MiniMax-M2.7 and is built by MiniMax.[e~[ ]~...". Open in app
2026-04-09MiniMaxAI/MiniMax-M2.7declared dtype unset to "bfloat16" (2026-04-09). Open in app
2026-04-09jinaai/jina-reranker-m0template rendering-changedthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-09). Open in app
2026-04-08mixedbread-ai/mxbai-rerank-large-v2template unrenderedthe chat template text changed; the renderer could not run one of the two versions, so whether rendered prompts changed is not known (2026-04-08). Open in app
2026-04-07nomic-ai/nomic-embed-text-v1.5structural tokenizerhead dim 64 declared (it was unset, so the library default for the class applied); our reconstruction builds the same graph from both configs (same parameter count and structure); context window 8192 to 2048 tokens; rope_theta unset to 1000; every position embedding changes (2026-04-07). Open in app
2026-04-07nomic-ai/nomic-embed-text-v1structural tokenizerhead dim 64 declared (it was unset, so the library default for the class applied); our reconstruction builds the same graph from both configs (same parameter count and structure); rope_scaling added ({"factor":2,"rope_type":"dynamic"}); positions are now scaled; rope_theta unset to 1000; every position embedding changes (2026-04-07). Open in app
2026-04-02nvidia/Gemma-4-31B-IT-NVFP4tokenizerpad token "<eos>" to "<pad>"; batched training masks a different id (2026-04-02). Open in app
2026-03-30nvidia/llama-nemotron-embed-1b-v2format-onlyformat-only re-save, RoPE settings rewritten in the transformers v5 rope_parameters form with the same values; nothing it computes, tokenises or generates changed (2026-03-30). Open in app
2026-03-16nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16generation-defaultsgeneration defaults changed (temperature unset to 1, top_p unset to 0.95); a call that does not pass these explicitly now generates differently (2026-03-16). Open in app
2026-03-11zai-org/GLM-5template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-03-11). Open in app
2026-03-09stepfun-ai/Step-3.5-Flashstructuralderived parameters 8.28B to 8.81B only because our reconstruction stops falling back to its own default; whether the loaded model changed depends on the library default, which this record does not check; tie_word_embeddings unset to false; the output head is no longer shared with the embedding (2026-03-09). Open in app
2026-03-06sarvamai/sarvam-30bstructuralcontext window 32768 to 131072 tokens (2026-03-06). Open in app
2026-03-04nvidia/Kimi-K2.5-NVFP4structuralquantization_config changed; the stored format of the weights is different (2026-03-04). Open in app
2026-03-04sarvamai/sarvam-30bstructuralcontext window 131072 to 32768 tokens (2026-03-04). Open in app
2026-03-02unsloth/Qwen3.5-9B-GGUFtemplate rendering-changed generation prefixthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-03-02).generation prefix: With add_generation_prompt, what follows the user's message changed from "<|im_end|>\n<|im_start|>assistant\n<think>\n" to "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n". Open in app
2026-03-01Qwen/Qwen3.5-0.8Btemplate rendering-changed generation prefixthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-03-01).generation prefix: With add_generation_prompt, what follows the user's message changed from "<|im_end|>\n<|im_start|>assistant\n<think>\n" to "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n". Open in app
2026-03-01Qwen/Qwen3.5-2Btemplate rendering-changed generation prefixthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-03-01).generation prefix: With add_generation_prompt, what follows the user's message changed from "<|im_end|>\n<|im_start|>assistant\n<think>\n" to "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n". Open in app
2026-03-01Qwen/Qwen3.5-0.8Btokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 131072 to 262144; truncation defaults change (2026-03-01). Open in app
2026-03-01Qwen/Qwen3.5-2Btokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 131072 to 262144; truncation defaults change (2026-03-01). Open in app
2026-03-01Qwen/Qwen3.5-9Btokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 131072 to 262144; truncation defaults change (2026-03-01). Open in app
2026-03-01Qwen/Qwen3.5-4Btokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 131072 to 262144; truncation defaults change (2026-03-01). Open in app
2026-02-27amd/DeepSeek-R1-MXFP4structuralquantization_config changed; the stored format of the weights is different (2026-02-27). Open in app
2026-02-24Qwen/Qwen3.5-27Btokenizertokenizer_class "Qwen3_5Tokenizer" to "Qwen2Tokenizer" (2026-02-24). Open in app
2026-02-24Qwen/Qwen3.5-35B-A3Btokenizertokenizer_class "Qwen3_5Tokenizer" to "Qwen2Tokenizer" (2026-02-24). Open in app
2026-02-24Qwen/Qwen3.5-27Btokenizertokenizer_class "Qwen2Tokenizer" to "Qwen3_5Tokenizer" (2026-02-24). Open in app
2026-02-24Qwen/Qwen3.5-35B-A3Btokenizertokenizer_class "Qwen2Tokenizer" to "Qwen3_5Tokenizer" (2026-02-24). Open in app
2026-02-24Qwen/Qwen3.5-27Btokenizertokenizer model_max_length 131072 to 262144; truncation defaults change (2026-02-24). Open in app
2026-02-24Qwen/Qwen3.5-27Btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-02-24). Open in app
2026-02-24Qwen/Qwen3.5-35B-A3Btokenizertokenizer model_max_length 131072 to 262144; truncation defaults change (2026-02-24). Open in app
2026-02-24Qwen/Qwen3.5-35B-A3Btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2026-02-24). Open in app
2026-02-19jinaai/jina-embeddings-v5-text-nano-retrievaltokenizertokenizer_class "TokenizersBackend" to "PreTrainedTokenizer" (2026-02-19). Open in app
2026-02-16jinaai/jina-embeddings-v5-text-nano-retrievalformat-onlyformat-only re-save, RoPE settings rewritten in the transformers v5 rope_parameters form with the same values; tokenizer class renamed between its Fast and plain spelling (one class per model since transformers v5); nothing it computes, tokenises or generates changed (2026-02-16). Open in app
2026-02-16jinaai/jina-embeddings-v5-text-nano-retrievalstructuralmodel_type "jina_embeddings_v5" to "eurobert"; a different class is instantiated from the same id (2026-02-16). Open in app
2026-02-12MiniMaxAI/MiniMax-M2.5template rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-02-12).default system prompt: With no system message, the text rendered before the user's message changed: "...are a helpful assistant.[e~[ ]~b]user" became "...are a helpful assistant. Your name is MiniMax-M2.5 and is built by MiniMax.[e~[ ]~...". Open in app
2026-02-11jinaai/jina-embeddings-v5-text-nano-retrievalstructuralarchitectures ["EuroBertForMaskedLM"] to ["EuroBertModel"]; a different class is instantiated from the same id (2026-02-11). Open in app
2026-02-10jinaai/jina-embeddings-v5-text-nano-retrievalstructuralarchitectures ["EuroBertModel"] to ["EuroBertForMaskedLM"]; a different class is instantiated from the same id (2026-02-10). Open in app
2026-02-02jinaai/jina-embeddings-v5-text-smallstructuralderived parameters 596.0M to 537.4M (-58.6M) only because the reconstruction follows the class name; no size key changed; context window 40960 to 32768 tokens; model_type "qwen3" to "jina_embeddings_v5"; a different class is instantiated from the same id (2026-02-02). Open in app
2026-02-02jinaai/jina-embeddings-v5-text-nanostructuralrope_theta 250000 to 1000000; every position embedding changes (2026-02-02). Open in app
2026-02-02stepfun-ai/Step-3.5-Flashgeneration-defaultsgeneration_config.json was removed; whatever defaults it set now come from the library (2026-02-02). Open in app
2026-01-30unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUFtemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-01-30). Open in app
2026-01-29unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUFtemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-01-29). Open in app
2026-01-29moonshotai/Kimi-K2.5template rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-01-29).default system prompt: With no system message, the text rendered before the user's message removed: "system You are Kimi, an AI assistant created by Moonshot AI. user" became "user". Open in app
2026-01-28sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2tokenizertokenizer_class unset to "PreTrainedTokenizerFast" (2026-01-28). Open in app
2025-12-15nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-12-15). Open in app
2025-12-15nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-12-15). Open in app
2025-12-10allenai/Olmo-3-7B-Thinkgeneration-defaultsgeneration defaults changed (do_sample unset to true); a call that does not pass these explicitly now generates differently (2025-12-10). Open in app
2025-12-08MiniMaxAI/MiniMax-M2template rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-12-08).default system prompt: With no system message, the text rendered before the user's message changed: "]~b]system You are a helpful assistant.[e~[ ]~b]user" became "]~b]system You are MiniMax-M2, a helpful AI assistant built by MiniMax. Knowledge cut...". Open in app
2025-12-06nvidia/Qwen2.5-VL-7B-Instruct-NVFP4structuralquantization_config changed; the stored format of the weights is different (2025-12-06). Open in app
2025-12-05cjvt/GaMS3-12B-Instructgeneration-defaultsgeneration defaults changed (temperature 0.2 to 0.6, top_k unset to 64, top_p 0.7 to 0.95); a call that does not pass these explicitly now generates differently (2025-12-05). Open in app
2025-12-05cjvt/GaMS3-12B-Instructgeneration-defaultsgeneration_config.json is still in the repository but is no longer valid JSON, so none of its settings can be read from it (2025-12-05). Open in app
2025-12-03Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8structural tokenizerconfig.json BOS declared as 151643 (was unset); MLP width 5472 to 6144; our reconstruction builds the same graph from both configs (same parameter count and structure); quantization_config changed; the stored format of the weights is different (2025-12-03). Open in app
2025-12-03Qwen/Qwen3-Coder-30B-A3B-Instructstructural tokenizerconfig.json BOS declared as 151643 (was unset); MLP width 5472 to 6144; our reconstruction builds the same graph from both configs (same parameter count and structure) (2025-12-03). Open in app
2025-12-01deepseek-ai/DeepSeek-V3.2generation-defaultsgeneration defaults changed (temperature 0.6 to 1); a call that does not pass these explicitly now generates differently (2025-12-01). Open in app
2025-11-26allenai/Olmo-3-7B-Instructgeneration-defaultsgeneration defaults changed (do_sample unset to true); a call that does not pass these explicitly now generates differently (2025-11-26). Open in app
2025-11-21allenai/Olmo-3-7B-Instructgeneration-defaultsgeneration defaults changed (max_new_tokens unset to 32768, temperature unset to 0.6, top_p unset to 0.95); a call that does not pass these explicitly now generates differently (2025-11-21). Open in app
2025-11-21allenai/Olmo-3-7B-Thinkgeneration-defaultsgeneration defaults changed (max_new_tokens unset to 32768, temperature unset to 0.6, top_p unset to 0.95); a call that does not pass these explicitly now generates differently (2025-11-21). Open in app
2025-11-14swiss-ai/Apertus-8B-Instruct-2509template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-11-14). Open in app
2025-11-07MiniMaxAI/MiniMax-M2template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-11-07). Open in app
2025-11-06MiniMaxAI/MiniMax-M2structural tokenizerEOS declared as 200020 (was unset); generation that relied on the library default now stops on this token; generation_config.json BOS declared as 200019 (was unset); model_type "minimax" to "minimax_m2"; a different class is instantiated from the same id (2025-11-06). Open in app
2025-10-31allenai/Olmo-3-7B-Thinkstructuralarchitectures ["Olmo2RetrofitForCausalLM"] to ["Olmo3ForCausalLM"]; a different class is instantiated from the same id (2025-10-31). Open in app
2025-10-27MiniMaxAI/MiniMax-M2structuralmodel_type "mixtral" to "minimax"; a different class is instantiated from the same id (2025-10-27). Open in app
2025-10-27MiniMaxAI/MiniMax-M2generation-defaultsgeneration defaults changed (top_k unset to 40); a call that does not pass these explicitly now generates differently (2025-10-27). Open in app
2025-10-25MiniMaxAI/MiniMax-M2structuralarchitectures ["MiniMaxM2MiniForCausalLM"] to ["MiniMaxM2ForCausalLM"]; a different class is instantiated from the same id (2025-10-25). Open in app
2025-10-22moonshotai/Kimi-K2-Instructtemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-10-22). Open in app
2025-10-22moonshotai/Kimi-K2-Instructtemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-10-22). Open in app
2025-10-10moonshotai/Kimi-K2-Instructtemplate rendering-changedthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-10-10). Open in app
2025-10-08nvidia/Qwen2.5-VL-7B-Instruct-NVFP4format-onlyformat-only re-save, RoPE settings rewritten in the transformers v5 rope_parameters form with the same values; nothing it computes, tokenises or generates changed (2025-10-08). Open in app
2025-10-04amd/DeepSeek-R1-MXFP4structuralquantization_config changed; the stored format of the weights is different (2025-10-04). Open in app
2025-09-23ai-sage/Giga-Embeddings-instructstructural tokenizermodel_type "gigar" to "gigarembed"; a different class is instantiated from the same id; declared dtype "bfloat16" to "float32"; tokenizer_class "PreTrainedTokenizerFast" to "PreTrainedTokenizer" (2025-09-23). Open in app
2025-09-23ai-sage/Giga-Embeddings-instructstructural templatehead dim 128 to 64, KV heads 2 to 16; derived parameters 3.30B to 2.50B (-801.0M, -1.60 GB of bf16 weights); rope_theta 1300 to 100000; every position embedding changes (2025-09-23). Open in app
2025-09-22PrimeIntellect/Qwen3-0.6Bstructural template rendering-changed default system promptdeclared dtype "float32" to "bfloat16"; the chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-09-22).default system prompt: With no system message, the text rendered before the user's message removed: "system You are Qwen, created by Alibaba Cloud. You are a helpful assistant. user" became "user". Open in app
2025-09-17Qwen/Qwen3-4B-Instruct-2507-FP8tokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 262144 to 1010000; truncation defaults change (2025-09-17). Open in app
2025-09-17Qwen/Qwen3-4B-Instruct-2507tokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 262144 to 1010000; truncation defaults change (2025-09-17). Open in app
2025-09-17Qwen/Qwen3-30B-A3B-Instruct-2507template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-09-17). Open in app
2025-09-17Qwen/Qwen3-30B-A3B-Instruct-2507-FP8tokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 262144 to 1010000; truncation defaults change (2025-09-17). Open in app
2025-09-17Qwen/Qwen3-235B-A22B-Instruct-2507-FP8tokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 262144 to 1010000; truncation defaults change (2025-09-17). Open in app
2025-09-11OpenGVLab/InternVL3-8Btemplate rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-09-11).default system prompt: With no system message, the text rendered before the user's message added: "user" became "system 你是书生·万象,英文名是InternVL,是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。 user". Open in app
2025-09-11OpenGVLab/InternVL3-1Btemplate rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-09-11).default system prompt: With no system message, the text rendered before the user's message added: "user" became "system 你是书生·万象,英文名是InternVL,是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。 user". Open in app
2025-09-11OpenGVLab/InternVL2_5-4Btemplate rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-09-11).default system prompt: With no system message, the text rendered before the user's message added: "user" became "system 你是书生·万象,英文名是InternVL,是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。 user". Open in app
2025-09-11OpenGVLab/InternVL2_5-4Btemplate rendering-changed default system prompt tool blockthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-09-11).default system prompt: With no system message, the text rendered before the user's message removed: "system You are Qwen, created by Alibaba Cloud. You are a helpful assistant. user" became "user".tool block: A tool list passed to the template reached the prompt before and is dropped now. Open in app
2025-09-11OpenGVLab/InternVL3-1Btemplate rendering-changed default system prompt tool blockthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-09-11).default system prompt: With no system message, the text rendered before the user's message removed: "system You are Qwen, created by Alibaba Cloud. You are a helpful assistant. user" became "user".tool block: A tool list passed to the template reached the prompt before and is dropped now. Open in app
2025-09-11OpenGVLab/InternVL3-8Btemplate rendering-changed default system prompt tool blockthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-09-11).default system prompt: With no system message, the text rendered before the user's message removed: "system You are Qwen, created by Alibaba Cloud. You are a helpful assistant. user" became "user".tool block: A tool list passed to the template reached the prompt before and is dropped now. Open in app
2025-09-01swiss-ai/Apertus-8B-Instruct-2509template rendering-changed default system promptthe chat template changed and renders differently (multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-09-01).default system prompt: With no system message, the text rendered before the user's message changed: "Deliberation: disabled T..." became "You are Apertus, a helpful assistant created by the SwissAI initiative. Knowledge cut...". Open in app
2025-09-01swiss-ai/Apertus-8B-Instruct-2509template rendering-changed default system promptthe chat template changed and renders differently (multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-09-01).default system prompt: With no system message, the text rendered before the user's message changed: "You are Apertus, a helpful assistant created by the SwissAI initiative. Knowledge cut..." became "Deliberation: disabled T...". Open in app
2025-08-26deepseek-ai/DeepSeek-V3.1structuralquantization_config changed; the stored format of the weights is different (2025-08-26). Open in app
2025-08-21nvidia/NVIDIA-Nemotron-Nano-9B-v2tokenizertokenizer model_max_length 1e+30 to 131072; truncation defaults change (2025-08-21). Open in app
2025-08-21Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8template rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-21). Open in app
2025-08-21Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8template rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-21). Open in app
2025-08-21Qwen/Qwen3-Coder-30B-A3B-Instructtemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-21). Open in app
2025-08-21Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8template unrenderedthe chat template text changed; the renderer could not run one of the two versions, so whether rendered prompts changed is not known (2025-08-21). Open in app
2025-08-21nvidia/NVIDIA-Nemotron-Nano-9B-v2tokenizerconfig.json eos_token_id 2 to 12, but generation_config.json still declares [2,11,12], which generate() reads first, so default generation stops on the same tokens; only code that reads config.eos_token_id directly sees the new value (2025-08-21). Open in app
2025-08-20mixedbread-ai/mxbai-rerank-large-v2tokenizerconfig.json pad_token_id unset to 151645; the tokenizer's pad token, which training pads with, did not change (2025-08-20). Open in app
2025-08-15nvidia/NVIDIA-Nemotron-Nano-9B-v2tokenizer template rendering-changed tool blockthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering; add_bos_token true to false; encoding the same text yields different ids (2025-08-15).tool block: A tool list passed to the template is rendered into the prompt now and was dropped before. Open in app
2025-08-13openai/gpt-oss-120btokenizer stop tokensEOS stop list [200002,199999] to [200002,199999,200012]; generation now also stops on 200012, and still stops on every token it stopped on before (2025-08-13).stop tokens: generation_config now stops on <|call|>, which ends a tool call in the template; before, nothing in its stop list did. Open in app
2025-08-13openai/gpt-oss-20btokenizer stop tokensEOS stop list [200002,199999] to [200002,199999,200012]; generation now also stops on 200012, and still stops on every token it stopped on before (2025-08-13).stop tokens: generation_config now stops on <|call|>, which ends a tool call in the template; before, nothing in its stop list did. Open in app
2025-08-11moonshotai/Kimi-K2-Instructtemplate rendering-changedthe chat template changed and renders differently (system+user, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-11). Open in app
2025-08-11moonshotai/Kimi-K2-Instructtemplate rendering-changedthe chat template changed and renders differently (system+user, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-11). Open in app
2025-08-08openai/gpt-oss-20btemplate rendering-changedthe chat template changed and renders differently (system+user, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-08). Open in app
2025-08-08openai/gpt-oss-120btemplate rendering-changedthe chat template changed and renders differently (system+user, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-08). Open in app
2025-08-08Qwen/Qwen3-30B-A3B-Instruct-2507tokenizertokenizer model_max_length 262144 to 1010000; truncation defaults change (2025-08-08). Open in app
2025-08-07openai/gpt-oss-120btemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-07). Open in app
2025-08-07openai/gpt-oss-20btemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-07). Open in app
2025-08-07Qwen/Qwen3-Coder-30B-A3B-Instructtemplate unrenderedthe chat template text changed; the renderer could not run one of the two versions, so whether rendered prompts changed is not known (2025-08-07). Open in app
2025-08-07Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8template unrenderedthe chat template text changed; the renderer could not run one of the two versions, so whether rendered prompts changed is not known (2025-08-07). Open in app
2025-08-06unsloth/gpt-oss-20b-GGUFstructural declared dtype unset to "bfloat16"; quantization_config changed; the stored format of the weights is different (2025-08-06). Open in app
2025-08-05unsloth/gpt-oss-20b-BF16template rendering-changed default system promptthe chat template changed and renders differently (system+user, multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-05).default system prompt: With no system message, the text rendered before the user's message changed: "...uded for every message. user" became "...uded for every message. Calls to these tools must go to the commentary channel: 'f...". Open in app
2025-08-05openai/gpt-oss-120btemplate rendering-changed default system promptthe chat template changed and renders differently (system+user, multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-05).default system prompt: With no system message, the text rendered before the user's message changed: "...uded for every message. Calls to these tools must go to the commentary channel: 'f..." became "...uded for every message. user". Open in app
2025-08-05openai/gpt-oss-20btemplate rendering-changed default system promptthe chat template changed and renders differently (system+user, multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-05).default system prompt: With no system message, the text rendered before the user's message changed: "...uded for every message. Calls to these tools must go to the commentary channel: 'f..." became "...uded for every message. user". Open in app
2025-08-05unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUFtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-08-05). Open in app
2025-07-31Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8tokenizer generation-defaultsEOS stop list 151645 to [151645,151643]; generation now also stops on 151643, and still stops on every token it stopped on before; generation_config.json pad_token_id unset to 151643; generate() fills finished sequences in a batch with this id, while training pads with the tokenizer's pad token, which did not change; generation defaults changed (do_sample unset to true, repetition_penalty unset to 1.05, temperature unset to 0.7, top_k unset to 20); a call that does not pass these explicitly now generates differently (2025-07-31). Open in app
2025-07-29Qwen/Qwen3-30B-A3B-Instruct-2507generation-defaultsgeneration defaults changed (temperature 0.6 to 0.7, top_p 0.95 to 0.8); a call that does not pass these explicitly now generates differently (2025-07-29). Open in app
2025-07-29Qwen/Qwen3-30B-A3B-Instruct-2507-FP8tokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 131072 to 262144; truncation defaults change (2025-07-29). Open in app
2025-07-29Qwen/Qwen3-30B-A3B-Instruct-2507tokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 131072 to 262144; truncation defaults change (2025-07-29). Open in app
2025-07-29Qwen/Qwen3-30B-A3B-Instruct-2507generation-defaultsgeneration defaults changed (temperature 0.7 to 0.6, top_p 0.8 to 0.95); a call that does not pass these explicitly now generates differently (2025-07-29). Open in app
2025-07-29Qwen/Qwen3-30B-A3B-Instruct-2507-FP8tokenizer generation-defaultsEOS stop list 151645 to [151645,151643]; generation now also stops on 151643, and still stops on every token it stopped on before; generation_config.json pad_token_id unset to 151643; generate() fills finished sequences in a batch with this id, while training pads with the tokenizer's pad token, which did not change; generation defaults changed (do_sample unset to true, temperature unset to 0.7, top_k unset to 20, top_p unset to 0.8); a call that does not pass these explicitly now generates differently (2025-07-29). Open in app
2025-07-28HuggingFaceTB/SmolLM3-3Bstructuraltie_word_embeddings unset to true; the output head is now shared with the embedding (2025-07-28). Open in app
2025-07-28Qwen/Qwen3-30B-A3B-Instruct-2507-FP8structuralMLP width 5504 to 6144; our reconstruction builds the same graph from both configs (same parameter count and structure); context window 1048576 to 262144 tokens; quantization_config changed; the stored format of the weights is different (2025-07-28). Open in app
2025-07-28Qwen/Qwen3-30B-A3B-Instruct-2507structuralMLP width 5504 to 6144; our reconstruction builds the same graph from both configs (same parameter count and structure); context window 1048576 to 262144 tokens; architectures ["Qwen2MoeForCausalLM"] to ["Qwen3MoeForCausalLM"]; a different class is instantiated from the same id (2025-07-28). Open in app
2025-07-22Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8tokenizer generation-defaultsEOS stop list 151645 to [151645,151643]; generation now also stops on 151643, and still stops on every token it stopped on before; generation_config.json BOS 151643 removed; generation_config.json pad_token_id unset to 151643; generate() fills finished sequences in a batch with this id, while training pads with the tokenizer's pad token, which did not change (2025-07-22). Open in app
2025-07-22hmellor/Ilama-3.2-1Bstructuralarchitectures ["LlamaForCausalLM"] to ["IlamaForCausalLM"]; a different class is instantiated from the same id (2025-07-22). Open in app
2025-07-21Qwen/Qwen3-235B-A22B-Instruct-2507-FP8tokenizer generation-defaultsEOS stop list 151645 to [151645,151643]; generation now also stops on 151643, and still stops on every token it stopped on before; generation_config.json pad_token_id unset to 151643; generate() fills finished sequences in a batch with this id, while training pads with the tokenizer's pad token, which did not change; generation defaults changed (do_sample unset to true, temperature unset to 0.7, top_k unset to 20, top_p unset to 0.8); a call that does not pass these explicitly now generates differently (2025-07-21). Open in app
2025-07-21Qwen/Qwen3-235B-A22B-Instruct-2507-FP8tokenizer template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered; tokenizer model_max_length 131072 to 262144; truncation defaults change (2025-07-21). Open in app
2025-07-21Qwen/Qwen3-235B-A22B-Instruct-2507-FP8structuralMLP width 10944 to 12288; our reconstruction builds the same graph from both configs (same parameter count and structure); context window 1048576 to 262144 tokens; quantization_config changed; the stored format of the weights is different (2025-07-21). Open in app
2025-07-18moonshotai/Kimi-K2-Instructtemplate rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-07-18).default system prompt: With no system message, the text rendered before the user's message changed: "system You are a helpful assistant user" became "system You are Kimi, an AI assistant created by Moonshot AI. user". Open in app
2025-07-15moonshotai/Kimi-K2-Instructtemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-07-15). Open in app
2025-07-15moonshotai/Kimi-K2-Instructtemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-07-15). Open in app
2025-07-10tomaarsen/Qwen3-Reranker-0.6B-seq-clstemplatethe chat template was removed (2025-07-10). Open in app
2025-07-09HuggingFaceTB/SmolLM3-3Btemplate unrenderedthe chat template text changed; the renderer could not run one of the two versions, so whether rendered prompts changed is not known (2025-07-09). Open in app
2025-07-08HuggingFaceTB/SmolLM3-3Btemplate rendering-changed default system prompt tool blockthe chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-07-08).default system prompt: With no system message, the text rendered before the user's message changed: "...o reach the conclusion. ## Tools ### XML Tools None ### Python Tools None user" became "...o reach the conclusion. user".tool block: A tool list passed to the template reached the prompt before and is dropped now. Open in app
2025-07-08HuggingFaceTB/SmolLM3-3Bgeneration-defaultsgeneration defaults changed (do_sample unset to true, temperature unset to 0.6, top_p unset to 0.95); a call that does not pass these explicitly now generates differently (2025-07-08). Open in app
2025-07-08HuggingFaceTB/SmolLM3-3Btokenizerconfig.json eos_token_id 128001 to 128012, but generation_config.json still declares 128012, which generate() reads first, so default generation stops on the same tokens; only code that reads config.eos_token_id directly sees the new value (2025-07-08). Open in app
2025-07-03jinaai/jina-embeddings-v4derived parameters 2.80B to 3.09B (+288.2M) only because the reconstruction follows the class name; no size key changed; model_type declared as "qwen2_5_vl_text" (was unset) (2025-07-03). Open in app
2025-06-21vikhyatk/moondream2structuraldeclared dtype "float16" to "bfloat16" (2025-06-21). Open in app
2025-06-12amd/DeepSeek-R1-MXFP4tokenizertokenizer model_max_length 512 to 16384; truncation defaults change (2025-06-12). Open in app
2025-06-06tomaarsen/Qwen3-Reranker-0.6B-seq-clsstructural tokenizerarchitectures ["Qwen3ForCausalLM"] to ["Qwen3ForSequenceClassification"]; a different class is instantiated from the same id; declared dtype "bfloat16" to "float32"; config.json pad_token_id unset to 151643; the tokenizer's pad token, which training pads with, did not change (2025-06-06). Open in app
2025-06-05Qwen/Qwen3-Embedding-4Bstructuralarchitectures ["Qwen3Model"] to ["Qwen3ForCausalLM"]; a different class is instantiated from the same id (2025-06-05). Open in app
2025-06-05Qwen/Qwen3-Embedding-8Bstructuralarchitectures ["Qwen3Model"] to ["Qwen3ForCausalLM"]; a different class is instantiated from the same id (2025-06-05). Open in app
2025-06-04ai-sage/Giga-Embeddings-instructstructuralcontext window 32768 to 4096 tokens (2025-06-04). Open in app
2025-06-03Qwen/Qwen3-Embedding-0.6Bstructural tokenizer generation-defaults stop tokens stop tokensEOS stop list [151645,151643] to 151643; generation no longer stops on 151645 and runs past it; context window 40960 to 32768 tokens; generation_config.json pad_token_id 151643 to unset; generate() fills finished sequences in a batch with this id, while training pads with the tokenizer's pad token, which did not change (2025-06-03).stop tokens: generation_config no longer stops on any token that ends an answer in the template (<|im_end|> was dropped).stop tokens: generation_config no longer stops on any token that ends a tool call in the template (<|im_end|> was dropped). Open in app
2025-05-29deepseek-ai/DeepSeek-R1-0528-Qwen3-8Bstructuralrope_scaling rewritten in a different format ({"factor":4,"original_max_position_embeddings":32768,"rop... to {"attn_factor":0.8782488562869419,"factor":4,"original_ma...); a loader that only reads the old format rejects or ignores the new one (2025-05-29). Open in app
2025-05-29ai-sage/Giga-Embeddings-instructstructurallayer count 27 to 36; derived parameters 2.61B to 3.30B (+693.7M, +1.39 GB of bf16 weights) (2025-05-29). Open in app
2025-05-29deepseek-ai/DeepSeek-R1-0528template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-29). Open in app
2025-05-20Qwen/Qwen3-8B-Basetokenizer eos vs templateEOS changed from "<|im_end|>" to "<|endoftext|>"; anything fine-tuned or served against the old value stops at a different token (2025-05-20).eos vs template: The template ends an answer with <|im_end|>, and the tokenizer's eos_token is now <|endoftext|> (it was <|im_end|>, which the template used). An engine that stops on the tokenizer's eos alone does not stop at the end of the turn. Open in app
2025-05-20Qwen/Qwen3-4B-Basetokenizer eos vs templateEOS changed from "<|im_end|>" to "<|endoftext|>"; anything fine-tuned or served against the old value stops at a different token (2025-05-20).eos vs template: The template ends an answer with <|im_end|>, and the tokenizer's eos_token is now <|endoftext|> (it was <|im_end|>, which the template used). An engine that stops on the tokenizer's eos alone does not stop at the end of the turn. Open in app
2025-05-20Qwen/Qwen3-1.7B-Basetokenizer eos vs templateEOS changed from "<|im_end|>" to "<|endoftext|>"; anything fine-tuned or served against the old value stops at a different token (2025-05-20).eos vs template: The template ends an answer with <|im_end|>, and the tokenizer's eos_token is now <|endoftext|> (it was <|im_end|>, which the template used). An engine that stops on the tokenizer's eos alone does not stop at the end of the turn. Open in app
2025-05-20Qwen/Qwen3-0.6B-Basetokenizer eos vs templateEOS changed from "<|im_end|>" to "<|endoftext|>"; anything fine-tuned or served against the old value stops at a different token (2025-05-20).eos vs template: The template ends an answer with <|im_end|>, and the tokenizer's eos_token is now <|endoftext|> (it was <|im_end|>, which the template used). An engine that stops on the tokenizer's eos alone does not stop at the end of the turn. Open in app
2025-05-19Qwen/Qwen3-8B-FP8template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-8B-AWQtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-8Btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-4Btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-32B-AWQtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-32Btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-30B-A3Btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-235B-A22Btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-14B-FP8template cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-14B-AWQtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-14Btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-1.7Btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-19Qwen/Qwen3-0.6Btemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-19). Open in app
2025-05-16jinaai/jina-embeddings-v4structuralderived parameters 3.09B to 2.80B (-288.3M) only because the reconstruction follows the class name; no size key changed; architectures ["ColQwen25Duo"] to ["JinaEmbeddingsV4Model"]; a different class is instantiated from the same id (2025-05-16). Open in app
2025-05-09unsloth/Qwen3-1.7B-GGUFtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-05-09). Open in app
2025-05-08Qwen/Qwen3-8B-AWQstructuraldeclared dtype "bfloat16" to "float16" (2025-05-08). Open in app
2025-05-06fixie-ai/ultravox-v0_5-llama-3_2-1btokenizertokenizer_class "PreTrainedTokenizerFast" to "PreTrainedTokenizer" (2025-05-06). Open in app
2025-05-06DavidAU/Qwen3-8B-64k-Context-2X-Josiefied-Uncensoredstructuralcontext window 40960 to 65536 tokens (2025-05-06). Open in app
2025-05-06DavidAU/Qwen3-8B-64k-Context-2X-Josiefied-Uncensoredstructuralrope_scaling added ({"factor":2,"original_max_position_embeddings":32768,"typ...); positions are now scaled (2025-05-06). Open in app
2025-05-03Qwen/Qwen3-8B-AWQstructural tokenizer template generation-defaults rendering-changedEOS stop list 151645 to [151645,151643]; generation now also stops on 151643, and still stops on every token it stopped on before; generation_config.json BOS declared as 151643 (was unset); context window 65536 to 40960 tokens (2025-05-03). Open in app
2025-05-02Qwen/Qwen3-14B-GGUFtemplate rendering-changedthe chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-05-02). Open in app
2025-05-01Qwen/Qwen3-32B-AWQstructural tokenizer generation-defaultsEOS stop list 151645 to [151645,151643]; generation now also stops on 151643, and still stops on every token it stopped on before; generation_config.json BOS declared as 151643 (was unset); context window 65536 to 40960 tokens (2025-05-01). Open in app
2025-05-01Qwen/Qwen3-14B-AWQstructural tokenizer generation-defaultsEOS stop list 151645 to [151645,151643]; generation now also stops on 151643, and still stops on every token it stopped on before; generation_config.json BOS declared as 151643 (was unset); context window 65536 to 40960 tokens (2025-05-01). Open in app
2025-04-29unsloth/Qwen3-1.7B-GGUFtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-04-29). Open in app
2025-04-29unsloth/Qwen3-1.7B-GGUFtemplate cosmeticthe chat template text changed but rendered byte-identically on the three fixed conversations (system+user, multi-turn, tool call), all of which end on a user turn; a conversation ending on an assistant turn (training data, prefill) was not rendered (2025-04-29). Open in app
2025-04-28Qwen/Qwen3-8B-Basetemplate rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-04-28).default system prompt: With no system message, the text rendered before the user's message removed: "system You are a helpful assistant. user" became "user". Open in app
2025-04-28Qwen/Qwen3-8B-FP8tokenizer generation-defaultsEOS stop list 151645 to [151645,151643]; generation now also stops on 151643, and still stops on every token it stopped on before; generation_config.json BOS declared as 151643 (was unset); generation defaults changed (do_sample unset to true, temperature unset to 0.6, top_k unset to 20, top_p unset to 0.95); a call that does not pass these explicitly now generates differently (2025-04-28). Open in app
2025-04-28Qwen/Qwen3-4B-Basetemplate rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-04-28).default system prompt: With no system message, the text rendered before the user's message removed: "system You are a helpful assistant. user" became "user". Open in app
2025-04-28Qwen/Qwen3-1.7B-Basetemplate rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-04-28).default system prompt: With no system message, the text rendered before the user's message removed: "system You are a helpful assistant. user" became "user". Open in app
2025-04-28Qwen/Qwen3-14B-FP8tokenizer generation-defaultsEOS stop list 151645 to [151645,151643]; generation now also stops on 151643, and still stops on every token it stopped on before; generation_config.json BOS declared as 151643 (was unset); generation defaults changed (do_sample unset to true, temperature unset to 0.6, top_k unset to 20, top_p unset to 0.95); a call that does not pass these explicitly now generates differently (2025-04-28). Open in app
2025-04-28Qwen/Qwen3-0.6B-Basetemplate rendering-changed default system promptthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-04-28).default system prompt: With no system message, the text rendered before the user's message removed: "system You are a helpful assistant. user" became "user". Open in app
2025-04-28Qwen/Qwen3-235B-A22BstructuralMLP width 8192 to 12288; our reconstruction builds the same graph from both configs (same parameter count and structure) (2025-04-28). Open in app
2025-04-28Qwen/Qwen3-30B-A3BstructuralMLP width 8192 to 6144; our reconstruction builds the same graph from both configs (same parameter count and structure) (2025-04-28). Open in app
2025-04-24ibm-granite/granite-3.3-2b-instructtemplate rendering-changedthe chat template changed and renders differently (multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-04-24). Open in app
2025-04-24unsloth/Llama-3.2-3B-Instructtokenizertokenizer_class "PreTrainedTokenizerFast" to "PreTrainedTokenizer" (2025-04-24). Open in app

Showing the newest 300 of 741. Every row as JSON.

Licence and access

296 model card licence changes, 22 LICENSE file changes and 0 gating changes across 208 models.

DateModelKindWhat changed
2026-11-05ConwayResearch/Underdog-Saluki-27B-1.0licencemodel card licence changed from "apache-2.0" to "cc-by-nc-4.0"; use under the old terms needs re-checking against the new ones (2026-11-05).
2026-11-05ConwayResearch/Underdog-Saluki-27B-1.0licence-filethe LICENSE file's text changed (2026-11-05).
2026-11-02XHToken/Spark-X2.6-4B-GGUFlicence-filea LICENSE file was added (2026-11-02).
2026-10-12melcheikh/gemma-4-31B-it-qat-NVFP4-Blackwelllicencemodel card licence changed from "gemma" to {"license":"apache-2.0","license_link":"https://ai.google.dev/gemma/docs/gemma_4_license"}; use under the old terms needs re-checking against the new ones (2026-10-12).
2026-10-08kindlingai/glm-5.3-exlr8-k2-k3-k4licence-filethe LICENSE file's text changed (2026-10-08).
2026-10-08kindlingai/glm-5.3-exlr8-k2-k3-k4licence-filethe LICENSE file's text changed (2026-10-08).
2026-09-01webAI-Official/TwIL-LM3licencemodel card licence changed from {"license":"other","license_link":"https://huggingface.co/webAI-Official/webAI-ColVec1-4b/blob/main/LICENSE.md","license_name":"webai-non-commercial-license-ver.-1.0"} to {"license":"other","license_link":"https://huggingface.co/webAI-Official/TwIL-LM3/blob/main/LICENSE.md","license_name":"webai-non-commercial-license-ver.-1.0"}; use under the old terms needs re-checking against the new ones (2026-09-01).
2026-09-01farbodtavakkoli/OTel-2.0-LLM-31B-ITlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://ai.google.dev/gemma/docs/gemma_4_license"}; use under the old terms needs re-checking against the new ones (2026-09-01).
2026-08-29nvidia/Kimi-K2-Thinking-NVFP4licencemodel card licence changed from {"license":"other","license_name":"modified-mit"} to {"license":"other","license_name":"nvidia-open-model-license"}; use under the old terms needs re-checking against the new ones (2026-08-29).
2026-08-28unsloth/GLM-5.3-GGUFlicencemodel card licence changed from "other" to {"license":"other","license_name":"glm-5.3"}; use under the old terms needs re-checking against the new ones (2026-08-28).
2026-08-28zai-org/GLM-5.3licencemodel card licence changed from "other" to {"license":"other","license_name":"glm-5.3"}; use under the old terms needs re-checking against the new ones (2026-08-28).
2026-08-28zai-org/GLM-5.3licence-filethe LICENSE file's text changed (2026-08-28).
2026-08-28superwhisper/s1-mini-GGUFlicence-filethe LICENSE file's text changed (2026-08-28).
2026-08-27OBLITERATUS/Ornith-1.5-9B-OBLITERATEDlicencemodel card licence declared as "mit" (was undeclared) (2026-08-27).
2026-08-26nvidia/llama-nemotron-rerank-1b-v2licencemodel card licence changed from {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","license_name":"nvidia-open-model-license"} to {"license":"other","license_link":"https://openmdw.ai/license/1-1/","license_name":"openmdw-1.1"}; use under the old terms needs re-checking against the new ones (2026-08-26).
2026-08-26nvidia/llama-nemotron-rerank-1b-v2licence-filethe LICENSE file's text changed (2026-08-26).
2026-08-26ornith-ai/Ornith-1.5-9B-NVFP4licencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-9B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-26).
2026-08-19ornith-ai/Ornith-1.5-397B-NVFP4licencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-397B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-397B-FP8licencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-397B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-397B-GGUFlicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-397B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-35B-A3B-MLXlicencemodel card licence {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/blob/main/LICENSE"} removed; the card no longer states terms (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-35B-A3B-MLXlicencemodel card licence declared as {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/blob/main/LICENSE"} (was undeclared) (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-35B-A3B-NVFP4licencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-35B-A3B-FP8licencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-35B-A3B-GGUFlicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-9B-GGUFlicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-9B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-35B-A3Blicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-9Blicencemodel card licence changed from {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.5-9B/blob/main/LICENSE"} to {"license":"mit","license_link":"https://huggingface.co/ornith-ai/Ornith-1.5-9B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-9Blicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.5-9B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-35B-A3B-MLXlicencemodel card licence "mit" removed; the card no longer states terms (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-9B-MLX-8bitlicencemodel card licence "mit" removed; the card no longer states terms (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-9B-MLXlicencemodel card licence "mit" removed; the card no longer states terms (2026-08-19).
2026-08-19ornith-ai/Ornith-1.5-9B-MLX-4bitlicencemodel card licence "mit" removed; the card no longer states terms (2026-08-19).
2026-08-17superwhisper/s1-mini-GGUFlicencemodel card licence changed from "apache-2.0" to {"license":"other","license_link":"LICENSE","license_name":"s1-mini-license"}; use under the old terms needs re-checking against the new ones (2026-08-17).
2026-08-17superwhisper/s1-mini-GGUFlicence-filethe LICENSE file's text changed (2026-08-17).
2026-08-150bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUFlicencemodel card licence changed from "other" to "apache-2.0"; use under the old terms needs re-checking against the new ones (2026-08-15).
2026-08-08CMSManhattan/JiRackUltra_1blicencemodel card licence changed from "other" to "mit"; use under the old terms needs re-checking against the new ones (2026-08-08).
2026-08-06nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4licencemodel card licence declared as {"license":"other","license_link":"https://openmdw.ai/license/1-1/","license_name":"openmdw-1.1"} (was undeclared) (2026-08-06).
2026-07-24zeroentropy/zerank-2-rerankerlicencemodel card licence changed from "cc-by-nc-4.0" to "apache-2.0"; use under the old terms needs re-checking against the new ones (2026-07-24).
2026-07-23bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUFlicencemodel card licence declared as "apache-2.0" (was undeclared) (2026-07-23).
2026-07-03k2-fsa/OmniVoicelicencemodel card licence "apache-2.0" removed; the card no longer states terms (2026-07-03).
2026-06-25ornith-ai/Ornith-1.0-397B-FP8licencemodel card licence changed from {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B/blob/main/LICENSE"} to {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B-FP8/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-06-25).
2026-06-25ornith-ai/Ornith-1.0-35B-GGUFlicencemodel card licence changed from {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B/blob/main/LICENSE"} to {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-GGUF/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-06-25).
2026-06-25ornith-ai/Ornith-1.0-9B-GGUFlicencemodel card licence changed from {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B/blob/main/LICENSE"} to {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B-GGUF/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-06-25).
2026-06-25ornith-ai/Ornith-1.0-397B-FP8licencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-06-25).
2026-06-25ornith-ai/Ornith-1.0-35B-GGUFlicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-06-25).
2026-06-25ornith-ai/Ornith-1.0-9B-GGUFlicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-06-25).
2026-06-21ornith-ai/Ornith-1.0-9Blicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-06-21).
2026-06-21ornith-ai/Ornith-1.0-35Blicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-06-21).
2026-06-19z-lab/Qwen3.6-35B-A3B-DFlashlicencemodel card licence changed from "mit" to "apache-2.0"; use under the old terms needs re-checking against the new ones (2026-06-19).
2026-06-16amd/MiniMax-M3-MXFP4licencemodel card licence declared as {"license":"other","license_link":"LICENSE","license_name":"minimax-community"} (was undeclared) (2026-06-16).
2026-06-15tvall43/Qwen3.6-14B-A3B-FableVibes-GGUFlicencemodel card licence declared as "apache-2.0" (was undeclared) (2026-06-15).
2026-06-15tvall43/Qwen3.6-14B-A3B-FableVibes-GGUFlicencemodel card licence "apache-2.0" removed; the card no longer states terms (2026-06-15).
2026-05-24openbmb/MiniCPM5-1Blicencemodel card licence declared as "apache-2.0" (was undeclared) (2026-05-24).
2026-05-21biohub/ESMC-6Blicencemodel card licence changed from "mit" to {"license":["mit","other"],"license_link":"https://github.com/Biohub/esm/blob/main/THIRD_PARTY_NOTICE.md"}; use under the old terms needs re-checking against the new ones (2026-05-21).
2026-05-13nvidia/Kimi-K2.5-NVFP4licencemodel card licence changed from {"license":"other","license_name":"modified-mit"} to {"license":"other","license_name":"nvidia-open-model-license"}; use under the old terms needs re-checking against the new ones (2026-05-13).
2026-05-11nvidia/Gemma-4-26B-A4B-NVFP4licencemodel card licence changed from {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-and-model-evaluation-license","license_name":"nvidia-software-and-model-evaluation-license"} to {"license":"apache-2.0","license_link":"https://ai.google.dev/gemma/apache_2","license_name":"apache-license-2.0"}; use under the old terms needs re-checking against the new ones (2026-05-11).
2026-05-10antirez/deepseek-v4-gguflicencemodel card licence declared as "mit" (was undeclared) (2026-05-10).
2026-05-08antirez/deepseek-v4-gguflicencemodel card licence "mit" removed; the card no longer states terms (2026-05-08).
2026-05-01nvidia/Gemma-4-26B-A4B-NVFP4licencemodel card licence changed from "apache-2.0" to {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-and-model-evaluation-license","license_name":"nvidia-software-and-model-evaluation-license"}; use under the old terms needs re-checking against the new ones (2026-05-01).
2026-04-28nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16licencemodel card licence declared as {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-agreement/","license_name":"nvidia-open-model-agreement"} (was undeclared) (2026-04-28).
2026-04-25sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTPlicencemodel card licence changed from "other" to "apache-2.0"; use under the old terms needs re-checking against the new ones (2026-04-25).
2026-04-17MiniMaxAI/MiniMax-M2.7licencemodel card licence changed from {"license":"other","license_link":"https://github.com/MiniMax-AI/MiniMax-M2.7/blob/main/LICENSE","license_name":"modified-mit"} to {"license":"other","license_link":"https://github.com/MiniMax-AI/MiniMax-M2.7/blob/main/LICENSE","license_name":"other"}; use under the old terms needs re-checking against the new ones (2026-04-17).
2026-04-15nvidia/MiniMax-M2.5-NVFP4licencemodel card licence changed from {"license":"other","license_name":"modified-mit"} to {"license":"other","license_name":"nvidia-open-model-license"}; use under the old terms needs re-checking against the new ones (2026-04-15).
2026-04-15nvidia/Gemma-4-31B-IT-NVFP4licencemodel card licence changed from {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license","license_name":"nvidia-open-model-license"} to {"license":"other","license_link":"https://ai.google.dev/gemma/apache_2","license_name":"apache-license-2.0"}; use under the old terms needs re-checking against the new ones (2026-04-15).
2026-04-14MiniMaxAI/MiniMax-M2.7licence-filethe LICENSE file's text changed (2026-04-14).
2026-03-16nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16licencemodel card licence changed from {"license":"other","license_link":"LICENSE","license_name":"nvidia-open-model-license"} to {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","license_name":"nvidia-nemotron-open-model-license"}; use under the old terms needs re-checking against the new ones (2026-03-16).
2026-03-16nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16licencemodel card licence declared as {"license":"other","license_link":"LICENSE","license_name":"nvidia-open-model-license"} (was undeclared) (2026-03-16).
2026-03-16nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16licencemodel card licence {"license":"other","license_link":"LICENSE","license_name":"nvidia-open-model-license"} removed; the card no longer states terms (2026-03-16).
2026-03-15nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4licencemodel card licence changed from {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","license_name":"nvidia-open-model-license"} to {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","license_name":"nvidia-nemotron-open-model-license"}; use under the old terms needs re-checking against the new ones (2026-03-15).
2026-03-15nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16licencemodel card licence changed from {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","license_name":"nvidia-open-model-license"} to {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","license_name":"nvidia-nemotron-open-model-license"}; use under the old terms needs re-checking against the new ones (2026-03-15).
2026-03-15nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8licencemodel card licence changed from {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","license_name":"nvidia-open-model-license"} to {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","license_name":"nvidia-nemotron-open-model-license"}; use under the old terms needs re-checking against the new ones (2026-03-15).
2026-03-14nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16licencemodel card licence changed from {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","license_name":"nvidia-open-model-license"} to {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","license_name":"nvidia-nemotron-open-model-license"}; use under the old terms needs re-checking against the new ones (2026-03-14).
2026-03-14nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8licencemodel card licence changed from {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","license_name":"nvidia-open-model-license"} to {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","license_name":"nvidia-nemotron-open-model-license"}; use under the old terms needs re-checking against the new ones (2026-03-14).
2026-03-14nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4licencemodel card licence changed from {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","license_name":"nvidia-open-model-license"} to {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","license_name":"nvidia-nemotron-open-model-license"}; use under the old terms needs re-checking against the new ones (2026-03-14).
2026-03-03sarvamai/sarvam-30blicencemodel card licence declared as "apache-2.0" (was undeclared) (2026-03-03).
2026-02-27EleutherAI/pythia-14mlicencemodel card licence declared as "apache-2.0" (was undeclared) (2026-02-27).
2026-02-12MiniMaxAI/MiniMax-M2.5licencemodel card licence changed from {"license":"other","license_link":"https://github.com/MiniMax-AI/MiniMax-M2.1/blob/main/LICENSE","license_name":"modified-mit"} to {"license":"other","license_link":"https://github.com/MiniMax-AI/MiniMax-M2.5/blob/main/LICENSE","license_name":"modified-mit"}; use under the old terms needs re-checking against the new ones (2026-02-12).
2026-02-12MiniMaxAI/MiniMax-M2.5licencemodel card licence changed from "mit" to {"license":"other","license_link":"https://github.com/MiniMax-AI/MiniMax-M2.1/blob/main/LICENSE","license_name":"modified-mit"}; use under the old terms needs re-checking against the new ones (2026-02-12).
2026-02-08jinaai/jina-embeddings-v5-text-nanolicencemodel card licence declared as "cc-by-nc-4.0" (was undeclared) (2026-02-08).
2026-02-08jinaai/jina-embeddings-v5-text-smalllicencemodel card licence declared as "cc-by-nc-4.0" (was undeclared) (2026-02-08).
2026-02-03Qwen/Qwen3-Coder-Next-FP8licencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-02-03).
2026-02-03Qwen/Qwen3-Coder-Nextlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2026-02-03).
2026-02-01nvidia/Kimi-K2.5-NVFP4licencemodel card licence declared as {"license":"other","license_name":"modified-mit"} (was undeclared) (2026-02-01).
2026-01-27deepseek-ai/DeepSeek-OCR-2licencemodel card licence changed from "mit" to "apache-2.0"; use under the old terms needs re-checking against the new ones (2026-01-27).
2026-01-27deepseek-ai/DeepSeek-OCR-2licencemodel card licence changed from "apache-2.0" to "mit"; use under the old terms needs re-checking against the new ones (2026-01-27).
2026-01-27deepseek-ai/DeepSeek-OCR-2licencemodel card licence changed from "mit" to "apache-2.0"; use under the old terms needs re-checking against the new ones (2026-01-27).
2026-01-08Qwen/Qwen3-VL-Embedding-2Blicencemodel card licence declared as "apache-2.0" (was undeclared) (2026-01-08).
2026-01-07Qwen/Qwen3-VL-Embedding-2Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2026-01-07).
2026-01-04LiquidAI/LFM2.5-1.2B-Instruct-GGUFlicencemodel card licence declared as {"license":"other","license_link":"LICENSE","license_name":"lfm1.0"} (was undeclared) (2026-01-04).
2026-01-04LiquidAI/LFM2.5-1.2B-Instruct-GGUFlicencemodel card licence {"license":"other","license_link":"LICENSE","license_name":"lfm1.0"} removed; the card no longer states terms (2026-01-04).
2025-12-02nvidia/Kimi-K2-Thinking-NVFP4licencemodel card licence changed from "mit" to {"license":"other","license_name":"modified-mit"}; use under the old terms needs re-checking against the new ones (2025-12-02).
2025-12-01deepseek-ai/DeepSeek-V3.2licencemodel card licence declared as "mit" (was undeclared) (2025-12-01).
2025-11-13MiniMaxAI/MiniMax-M2licencemodel card licence changed from "mit" to {"license":"other","license_link":"https://github.com/MiniMax-AI/MiniMax-M2/blob/main/LICENSE","license_name":"modified-mit"}; use under the old terms needs re-checking against the new ones (2025-11-13).
2025-10-27MiniMaxAI/MiniMax-M2licencemodel card licence changed from "apache-2.0" to "mit"; use under the old terms needs re-checking against the new ones (2025-10-27).
2025-10-17nvidia/llama-embed-nemotron-8blicence-filethe LICENSE file's text changed (2025-10-17).
2025-10-16nvidia/llama-nemotron-embed-1b-v2licencemodel card licence changed from "other" to {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","license_name":"nvidia-open-model-license"}; use under the old terms needs re-checking against the new ones (2025-10-16).
2025-10-16nvidia/llama-nemotron-embed-1b-v2licencemodel card licence declared as "other" (was undeclared) (2025-10-16).
2025-10-05openbmb/MiniCPM-o-2_6licencemodel card licence declared as "apache-2.0" (was undeclared) (2025-10-05).
2025-09-23ai-sage/Giga-Embeddings-instructlicencemodel card licence declared as "mit" (was undeclared) (2025-09-23).
2025-09-23ai-sage/Giga-Embeddings-instructlicencemodel card licence "mit" removed; the card no longer states terms (2025-09-23).
2025-09-22PrimeIntellect/Qwen3-0.6Blicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-09-22).
2025-09-15openbmb/MiniCPM-V-4_5licencemodel card licence declared as "apache-2.0" (was undeclared) (2025-09-15).
2025-09-15openbmb/MiniCPM-V-4_5licencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-09-15).
2025-09-15openbmb/MiniCPM-V-4_5licencemodel card licence declared as "apache-2.0" (was undeclared) (2025-09-15).
2025-08-25openbmb/MiniCPM-V-4_5licencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-08-25).
2025-08-19jinaai/jina-embeddings-v4licencemodel card licence "cc-by-nc-4.0" removed; the card no longer states terms (2025-08-19).
2025-08-18nvidia/NVIDIA-Nemotron-Nano-9B-v2licencemodel card licence changed from "other" to {"license":"other","license_link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","license_name":"nvidia-open-model-license"}; use under the old terms needs re-checking against the new ones (2025-08-18).
2025-08-18nvidia/NVIDIA-Nemotron-Nano-9B-v2licencemodel card licence declared as "other" (was undeclared) (2025-08-18).
2025-08-13PrimeIntellect/Qwen3-0.6Blicencemodel card licence changed from "mit" to "apache-2.0"; use under the old terms needs re-checking against the new ones (2025-08-13).
2025-08-12PrimeIntellect/Qwen3-0.6Blicencemodel card licence declared as "mit" (was undeclared) (2025-08-12).
2025-08-06Qwen/Qwen3-4B-Instruct-2507-FP8licencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507-FP8/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-08-06).
2025-08-05openai/gpt-oss-20blicence-filethe LICENSE file's text changed (2025-08-05).
2025-08-05openai/gpt-oss-120blicence-filethe LICENSE file's text changed (2025-08-05).
2025-08-05Qwen/Qwen3-4B-Thinking-2507licencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-08-05).
2025-08-05Qwen/Qwen3-4B-Instruct-2507licencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-08-05).
2025-07-31unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUFlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-07-31).
2025-07-31Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8licencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-07-31).
2025-07-31Qwen/Qwen3-Coder-30B-A3B-Instructlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-07-31).
2025-07-29Qwen/Qwen3-30B-A3B-Instruct-2507-FP8licencemodel card licence changed from {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/main/LICENSE"} to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507-FP8/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-07-29).
2025-07-29Qwen/Qwen3-30B-A3B-Instruct-2507-FP8licence-filethe LICENSE file's text changed (2025-07-29).
2025-07-29Qwen/Qwen3-30B-A3B-Instruct-2507licence-filethe LICENSE file's text changed (2025-07-29).
2025-07-29Qwen/Qwen3-30B-A3B-Instruct-2507licencemodel card licence changed from {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/LICENSE"} to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-07-29).
2025-07-29Qwen/Qwen3-30B-A3B-Instruct-2507licencemodel card licence changed from {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/main/LICENSE"} to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-07-29).
2025-07-28Qwen/Qwen3-30B-A3B-Instruct-2507-FP8licencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-07-28).
2025-07-21Qwen/Qwen3-235B-A22B-Instruct-2507-FP8licencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-07-21).
2025-07-11moonshotai/Kimi-K2-Instructlicencemodel card licence changed from "mit" to {"license":"other","license_name":"modified-mit"}; use under the old terms needs re-checking against the new ones (2025-07-11).
2025-07-11moonshotai/Kimi-K2-Instructlicencemodel card licence declared as "mit" (was undeclared) (2025-07-11).
2025-07-11moonshotai/Kimi-K2-Instructlicencemodel card licence "mit" removed; the card no longer states terms (2025-07-11).
2025-07-08HuggingFaceTB/SmolLM3-3Blicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-07-08).
2025-06-24jinaai/jina-embeddings-v4licencemodel card licence declared as "cc-by-nc-4.0" (was undeclared) (2025-06-24).
2025-06-05Qwen/Qwen3-Embedding-0.6Blicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-06-05).
2025-06-03Qwen/Qwen3-Embedding-0.6Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-06-03).
2025-05-29ai-sage/Giga-Embeddings-instructlicencemodel card licence declared as "mit" (was undeclared) (2025-05-29).
2025-05-29ai-sage/Giga-Embeddings-instructlicencemodel card licence "mit" removed; the card no longer states terms (2025-05-29).
2025-05-08Qwen/Qwen3-0.6B-GGUFlicencemodel card licence changed from {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-1.7B-GGUF/blob/main/LICENSE"} to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-0.6B-GGUF/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-05-08).
2025-05-05Qwen/Qwen3-4B-GGUFlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-4B-GGUF/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-05-05).
2025-05-05Qwen/Qwen3-0.6B-GGUFlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-1.7B-GGUF/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-05-05).
2025-05-03Qwen/Qwen3-8B-GGUFlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-8B-GGUF/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-05-03).
2025-05-03Qwen/Qwen3-8B-AWQlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-05-03).
2025-05-01Qwen/Qwen3-14B-GGUFlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-14B-GGUF/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-05-01).
2025-05-01Qwen/Qwen3-32B-AWQlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-05-01).
2025-05-01Qwen/Qwen3-14B-AWQlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-14B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-05-01).
2025-04-28Qwen/Qwen3-8B-Baselicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-8B-FP8licencemodel card licence declared as {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-8B-FP8/blob/main/LICENSE"} (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-30B-A3Blicencemodel card licence declared as {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE"} (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-0.6Blicencemodel card licence declared as {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE"} (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-30B-A3Blicencemodel card licence {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE"} removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-1.7Blicencemodel card licence changed from {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-235B-A22B/blob/main/LICENSE"} to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-04-28).
2025-04-28Qwen/Qwen3-1.7Blicencemodel card licence declared as {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-235B-A22B/blob/main/LICENSE"} (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-4Blicencemodel card licence declared as {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE"} (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-8Blicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-04-28).
2025-04-28Qwen/Qwen3-14Blicencemodel card licence declared as {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-14B/blob/main/LICENSE"} (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-32Blicencemodel card licence declared as {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE"} (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-30B-A3Blicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-04-28).
2025-04-28Qwen/Qwen3-235B-A22Blicencemodel card licence declared as {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-235B-A22B/blob/main/LICENSE"} (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-8Blicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-32Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-30B-A3Blicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-235B-A22Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-14Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-8B-FP8licencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28unsloth/Qwen3-4B-GGUFlicencemodel card licence declared as {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE"} (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-32Blicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-4B-Baselicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-1.7B-Baselicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-235B-A22Blicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-0.6B-Baselicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-235B-A22Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-0.6Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-14Blicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-30B-A3Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-32Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-14Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-4Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-8Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-8B-Baselicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-4B-Baselicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-1.7Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-1.7B-Baselicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-0.6B-Baselicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-28Qwen/Qwen3-0.6Blicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-04-28).
2025-04-28Qwen/Qwen3-0.6Blicencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-04-28).
2025-04-25OpenGVLab/InternVL3-1Blicencemodel card licence changed from {"license":"other","license_link":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE","license_name":"qwen"} to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE","license_name":"qwen"}; use under the old terms needs re-checking against the new ones (2025-04-25).
2025-04-25OpenGVLab/InternVL3-8Blicencemodel card licence changed from {"license":"other","license_link":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE","license_name":"qwen"} to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE","license_name":"qwen"}; use under the old terms needs re-checking against the new ones (2025-04-25).
2025-02-28apple/OpenELM-1_1B-Instructlicencemodel card licence changed from {"license":"other","license_link":"LICENSE","license_name":"apple-sample-code-license"} to {"license":"apple-amlr","license_link":"LICENSE","license_name":"apple-sample-code-license"}; use under the old terms needs re-checking against the new ones (2025-02-28).
2025-02-25GSAI-ML/LLaDA-8B-Instructlicencemodel card licence changed from "apache-2.0" to "mit"; use under the old terms needs re-checking against the new ones (2025-02-25).
2025-02-24microsoft/Phi-4-multimodal-instructlicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct/resolve/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2025-02-24).
2025-02-24apple/OpenELM-1_1B-Instructlicence-filethe LICENSE file's text changed (2025-02-24).
2025-02-21google/siglip2-giant-opt-patch16-384licencemodel card licence declared as "apache-2.0" (was undeclared) (2025-02-21).
2025-02-11nomic-ai/nomic-embed-text-v2-moelicencemodel card licence declared as "apache-2.0" (was undeclared) (2025-02-11).
2025-02-07fixie-ai/ultravox-v0_5-llama-3_2-1blicencemodel card licence declared as "mit" (was undeclared) (2025-02-07).
2025-01-23deepseek-ai/DeepSeek-R1-Distill-Qwen-7Blicencemodel card licence declared as "mit" (was undeclared) (2025-01-23).
2025-01-23deepseek-ai/DeepSeek-R1-Distill-Qwen-32Blicencemodel card licence declared as "mit" (was undeclared) (2025-01-23).
2025-01-23deepseek-ai/DeepSeek-R1-Distill-Qwen-14Blicencemodel card licence declared as "mit" (was undeclared) (2025-01-23).
2025-01-23deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5Blicencemodel card licence declared as "mit" (was undeclared) (2025-01-23).
2025-01-21deepseek-ai/DeepSeek-R1licencemodel card licence declared as "mit" (was undeclared) (2025-01-21).
2025-01-15nomic-ai/CodeRankEmbedlicencemodel card licence declared as "mit" (was undeclared) (2025-01-15).
2025-01-14openbmb/MiniCPM-o-2_6licencemodel card licence "apache-2.0" removed; the card no longer states terms (2025-01-14).
2025-01-14openbmb/MiniCPM-o-2_6licencemodel card licence declared as "apache-2.0" (was undeclared) (2025-01-14).
2024-12-20ai-sage/Giga-Embeddings-instructlicencemodel card licence declared as "mit" (was undeclared) (2024-12-20).
2024-12-20ai-sage/Giga-Embeddings-instructlicencemodel card licence "mit" removed; the card no longer states terms (2024-12-20).
2024-12-13ai-sage/Giga-Embeddings-instructlicencemodel card licence declared as "mit" (was undeclared) (2024-12-13).
2024-12-12ai-sage/Giga-Embeddings-instructlicencemodel card licence "mit" removed; the card no longer states terms (2024-12-12).
2024-12-11microsoft/phi-4licencemodel card licence changed from {"license":"other","license_link":"https://huggingface.co/microsoft/phi-4/resolve/main/LICENSE"} to {"license":"mit","license_link":"https://huggingface.co/microsoft/phi-4/resolve/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-12-11).
2024-12-11microsoft/phi-4licence-filethe LICENSE file's text changed (2024-12-11).
2024-11-12jinaai/jina-clip-v2licencemodel card licence declared as "cc-by-nc-4.0" (was undeclared) (2024-11-12).
2024-11-11Qwen/Qwen2.5-Coder-3B-Instructlicencemodel card licence changed from {"license":"other","license_link":"https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE","license_name":"qwen-research"} to {"license":"other","license_link":"https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct/blob/main/LICENSE","license_name":"qwen-research"}; use under the old terms needs re-checking against the new ones (2024-11-11).
2024-10-31HuggingFaceTB/SmolLM2-135Mlicencemodel card licence declared as "apache-2.0" (was undeclared) (2024-10-31).
2024-10-31HuggingFaceTB/SmolLM2-135M-Instructlicencemodel card licence declared as "apache-2.0" (was undeclared) (2024-10-31).
2024-10-31HuggingFaceTB/SmolLM2-1.7B-Instructlicencemodel card licence declared as "apache-2.0" (was undeclared) (2024-10-31).
2024-10-31HuggingFaceTB/SmolLM2-360M-Instructlicencemodel card licence declared as "apache-2.0" (was undeclared) (2024-10-31).
2024-10-31HuggingFaceTB/SmolLM2-360Mlicencemodel card licence declared as "apache-2.0" (was undeclared) (2024-10-31).
2024-10-15hugging-quants/gemma-2-9b-it-AWQ-INT4licencemodel card licence declared as "gemma" (was undeclared) (2024-10-15).
2024-10-08jinaai/jina-clip-v2licencemodel card licence "cc-by-nc-4.0" removed; the card no longer states terms (2024-10-08).
2024-10-04openai/whisper-large-v3-turbolicencemodel card licence changed from "apache-2.0" to "mit"; use under the old terms needs re-checking against the new ones (2024-10-04).
2024-10-01openai/whisper-large-v3-turbolicencemodel card licence declared as "apache-2.0" (was undeclared) (2024-10-01).
2024-09-25unsloth/Llama-3.2-1B-Instructlicencemodel card licence declared as "llama3.2" (was undeclared) (2024-09-25).
2024-09-25unsloth/Llama-3.2-3B-Instructlicencemodel card licence declared as "llama3.2" (was undeclared) (2024-09-25).
2024-09-25meta-llama/Llama-3.2-1Blicencemodel card licence declared as "llama3.2" (was undeclared) (2024-09-25).
2024-09-25meta-llama/Llama-3.2-3Blicencemodel card licence declared as "llama3.2" (was undeclared) (2024-09-25).
2024-09-25meta-llama/Llama-3.2-1B-Instructlicencemodel card licence declared as "llama3.2" (was undeclared) (2024-09-25).
2024-09-25meta-llama/Llama-3.2-3B-Instructlicencemodel card licence declared as "llama3.2" (was undeclared) (2024-09-25).
2024-09-25Maple728/TimeMoE-50Mlicencemodel card licence changed from "mit" to "apache-2.0"; use under the old terms needs re-checking against the new ones (2024-09-25).
2024-09-25utter-project/EuroLLM-1.7B-Instructlicencemodel card licence declared as "apache-2.0" (was undeclared) (2024-09-25).
2024-09-24utter-project/EuroLLM-1.7B-Instructlicencemodel card licence "apache-2.0" removed; the card no longer states terms (2024-09-24).
2024-09-20meta-llama/Llama-3.2-1Blicence-filethe LICENSE.txt file's text changed (2024-09-20).
2024-09-19bartowski/Qwen2.5-32B-Instruct-GGUFlicencemodel card licence declared as {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE"} (was undeclared) (2024-09-19).
2024-09-19bartowski/Qwen2.5-32B-Instruct-GGUFlicencemodel card licence "apache-2.0" removed; the card no longer states terms (2024-09-19).
2024-09-18Qwen/Qwen2.5-Coder-7B-Instructlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-Coder-7Blicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-Coder-1.5B-Instructlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-Coder-1.5Blicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-7Blicencemodel card licence changed from {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-32B/blob/main/LICENSE"} to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-7B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-Math-1.5Blicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-Math-1.5B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-0.5Blicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-0.5B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-1.5Blicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-7Blicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-32B/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-7B-Instructlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-32B-Instructlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-14B-Instructlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-1.5B-Instructlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-0.5B-Instructlicencemodel card licence changed from "apache-2.0" to {"license":"apache-2.0","license_link":"https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-72B-Instructlicence-filethe LICENSE file's text changed (2024-09-18).
2024-09-18Qwen/Qwen2.5-72B-Instruct-AWQlicencemodel card licence changed from {"license":"other","license_link":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE","license_name":"qwen"} to {"license":"other","license_link":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct-AWQ/blob/main/LICENSE","license_name":"qwen"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-3B-Instructlicencemodel card licence changed from {"license":"other","license_link":"https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE","license_name":"tongyi-qianwen-research"} to {"license":"other","license_link":"https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE","license_name":"qwen-research"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-18Qwen/Qwen2.5-72B-Instructlicencemodel card licence changed from {"license":"other","license_link":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE","license_name":"tongyi-qianwen"} to {"license":"other","license_link":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE","license_name":"qwen"}; use under the old terms needs re-checking against the new ones (2024-09-18).
2024-09-17bartowski/Qwen2.5-32B-Instruct-GGUFlicencemodel card licence declared as "apache-2.0" (was undeclared) (2024-09-17).
2024-09-14stepfun-ai/GOT-OCR2_0licencemodel card licence declared as "apache-2.0" (was undeclared) (2024-09-14).
2024-08-20microsoft/Phi-3.5-vision-instructlicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/microsoft/Phi-3.5-vision-instruct/resolve/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-08-20).
2024-08-20microsoft/Phi-3.5-mini-instructlicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/microsoft/Phi-3.5-mini-instruct/resolve/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-08-20).
2024-08-20microsoft/Phi-3.5-MoE-instructlicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/microsoft/Phi-3.5-MoE-instruct/resolve/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-08-20).
2024-08-15NousResearch/Hermes-3-Llama-3.1-8Blicencemodel card licence declared as "llama3" (was undeclared) (2024-08-15).
2024-07-30bartowski/Meta-Llama-3.1-8B-Instruct-GGUFlicencemodel card licence declared as "llama3.1" (was undeclared) (2024-07-30).
2024-07-30bartowski/Meta-Llama-3.1-8B-Instruct-GGUFlicencemodel card licence "llama3.1" removed; the card no longer states terms (2024-07-30).
2024-07-28bartowski/Meta-Llama-3.1-8B-Instruct-GGUFlicencemodel card licence declared as "llama3.1" (was undeclared) (2024-07-28).
2024-07-28bartowski/Meta-Llama-3.1-8B-Instruct-GGUFlicencemodel card licence "llama3.1" removed; the card no longer states terms (2024-07-28).
2024-07-26BAAI/bge-reranker-v2.5-gemma2-lightweightlicencemodel card licence changed from "apache-2.0" to "gemma"; use under the old terms needs re-checking against the new ones (2024-07-26).
2024-07-24bartowski/Meta-Llama-3.1-8B-Instruct-GGUFlicencemodel card licence declared as "llama3.1" (was undeclared) (2024-07-24).
2024-07-24bartowski/Meta-Llama-3.1-8B-Instruct-GGUFlicencemodel card licence "llama3.1" removed; the card no longer states terms (2024-07-24).
2024-07-23bartowski/Meta-Llama-3.1-8B-Instruct-GGUFlicencemodel card licence declared as "llama3.1" (was undeclared) (2024-07-23).
2024-07-23bartowski/Meta-Llama-3.1-8B-Instruct-GGUFlicencemodel card licence "llama3.1" removed; the card no longer states terms (2024-07-23).
2024-07-23unsloth/Meta-Llama-3.1-8B-Instructlicencemodel card licence declared as "llama3.1" (was undeclared) (2024-07-23).
2024-07-23bartowski/Meta-Llama-3.1-8B-Instruct-GGUFlicencemodel card licence declared as "llama3.1" (was undeclared) (2024-07-23).
2024-07-23meta-llama/Llama-3.1-405B-FP8licencemodel card licence changed from "other" to "llama3.1"; use under the old terms needs re-checking against the new ones (2024-07-23).
2024-07-23meta-llama/Prompt-Guard-86Mlicencemodel card licence changed from "other" to "llama3.1"; use under the old terms needs re-checking against the new ones (2024-07-23).
2024-07-23meta-llama/Llama-3.1-8Blicencemodel card licence changed from "other" to "llama3.1"; use under the old terms needs re-checking against the new ones (2024-07-23).
2024-07-23meta-llama/Llama-3.1-8B-Instructlicencemodel card licence changed from "other" to "llama3.1"; use under the old terms needs re-checking against the new ones (2024-07-23).
2024-07-23meta-llama/Llama-3.1-405B-FP8licencemodel card licence declared as "other" (was undeclared) (2024-07-23).
2024-07-23meta-llama/Prompt-Guard-86Mlicencemodel card licence declared as "other" (was undeclared) (2024-07-23).
2024-07-22meta-llama/Llama-3.1-8Blicencemodel card licence declared as "other" (was undeclared) (2024-07-22).
2024-07-18RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8licencemodel card licence changed from {"license":"other","license_link":"LICENSE","license_name":"deepseek-license"} to {"license":"other","license_link":"https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/LICENSE-MODEL","license_name":"deepseek-license"}; use under the old terms needs re-checking against the new ones (2024-07-18).
2024-07-18RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8licencemodel card licence declared as {"license":"other","license_link":"LICENSE","license_name":"deepseek-license"} (was undeclared) (2024-07-18).
2024-07-16google/gemma-2-2b-itlicencemodel card licence declared as "gemma" (was undeclared) (2024-07-16).
2024-07-01microsoft/Phi-3-mini-128k-instructlicence-filethe LICENSE file's text changed (2024-07-01).
2024-07-01microsoft/Phi-3-mini-4k-instructlicence-filethe LICENSE file's text changed (2024-07-01).
2024-07-01PekingU/rtdetr_r101vd_coco_o365licencemodel card licence declared as "apache-2.0" (was undeclared) (2024-07-01).
2024-06-19jinaai/jina-reranker-v2-base-multilinguallicencemodel card licence declared as "cc-by-nc-4.0" (was undeclared) (2024-06-19).
2024-06-15microsoft/Florence-2-base-ftlicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/microsoft/Florence-2-base-ft/resolve/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-06-15).
2024-06-15microsoft/Florence-2-baselicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/microsoft/Florence-2-base/resolve/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-06-15).
2024-06-15microsoft/Florence-2-largelicencemodel card licence changed from "mit" to {"license":"mit","license_link":"https://huggingface.co/microsoft/Florence-2-large/resolve/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-06-15).
2024-06-07deepseek-ai/DeepSeek-V2-Lite-Chatlicencemodel card licence declared as {"license":"other","license_link":"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL","license_name":"deepseek"} (was undeclared) (2024-06-07).
2024-06-07deepseek-ai/DeepSeek-V2-Litelicencemodel card licence declared as {"license":"other","license_link":"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL","license_name":"deepseek"} (was undeclared) (2024-06-07).
2024-05-22unsloth/mistral-7b-v0.3-bnb-4bitlicencemodel card licence declared as "apache-2.0" (was undeclared) (2024-05-22).
2024-05-15deepseek-ai/DeepSeek-V2-Litelicencemodel card licence "mit" removed; the card no longer states terms (2024-05-15).
2024-05-04MahmoudAshraf/mms-300m-1130-forced-alignerlicencemodel card licence declared as "cc-by-nc-4.0" (was undeclared) (2024-05-04).
2024-05-04MahmoudAshraf/mms-300m-1130-forced-alignerlicencemodel card licence "cc-by-nc-4.0" removed; the card no longer states terms (2024-05-04).
2024-04-20IlyaGusev/saiga_llama3_8blicencemodel card licence declared as {"license":"other","license_link":"https://llama.meta.com/llama3/license/","license_name":"llama3"} (was undeclared) (2024-04-20).
2024-03-17BAAI/bge-reranker-v2-gemmalicencemodel card licence declared as "apache-2.0" (was undeclared) (2024-03-17).
2024-03-17BAAI/bge-reranker-v2-m3licencemodel card licence changed from "mit" to "apache-2.0"; use under the old terms needs re-checking against the new ones (2024-03-17).
2024-02-12nomic-ai/nomic-embed-text-v1.5licencemodel card licence declared as "apache-2.0" (was undeclared) (2024-02-12).
2024-02-06microsoft/phi-2licence-filethe LICENSE file's text changed (2024-02-06).
2024-01-09Qwen/Qwen-72Blicencemodel card licence declared as {"license":"other","license_link":"https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT","license_name":"tongyi-qianwen-license-agreement"} (was undeclared) (2024-01-09).
2024-01-05microsoft/phi-2licencemodel card licence changed from {"license":"other","license_link":"https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE","license_name":"microsoft-research-license"} to {"license":"mit","license_link":"https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE"}; use under the old terms needs re-checking against the new ones (2024-01-05).
2024-01-05microsoft/phi-2licence-filethe LICENSE file's text changed (2024-01-05).
2023-12-31TinyLlama/TinyLlama-1.1B-Chat-v1.0licencemodel card licence declared as "apache-2.0" (was undeclared) (2023-12-31).
2023-12-13microsoft/phi-2licencemodel card licence changed from {"license":"other","license_link":"https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx","license_name":"microsoft-research-license"} to {"license":"other","license_link":"https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE","license_name":"microsoft-research-license"}; use under the old terms needs re-checking against the new ones (2023-12-13).
2023-11-18Falconsai/nsfw_image_detectionlicencemodel card licence changed from "mit" to "apache-2.0"; use under the old terms needs re-checking against the new ones (2023-11-18).
2023-11-18Falconsai/nsfw_image_detectionlicencemodel card licence changed from "apache-2.0" to "mit"; use under the old terms needs re-checking against the new ones (2023-11-18).
2023-10-09jinaai/jina-embeddings-v2-small-enlicencemodel card licence declared as "apache-2.0" (was undeclared) (2023-10-09).

Lineage, as declared

Each tracked model that declares a base is checked against that base's card: a repo that calls itself a quantization of a base with no edit in its name while its own id or tags say abliterated, uncensored or heretic, and a derivative that declares a licence outside its base's family. These are statements about the card and tags, not about the weights or how the model behaves. 20 of 322 models with a declared base show one today.

ModelDeclared baseFinding
0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUFQwen/Qwen3.8-27Bedit-declared-as-quantization Declares itself a quantization of Qwen/Qwen3.8-27B, whose id names no edit, while its own id or tags say "Heretic". The model tree shows Qwen/Qwen3.8-27B as the direct parent with nothing in between.
Abiray/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUFISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUFedit-declared-as-quantization Declares itself a quantization of ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF, whose id names no edit, while its own id or tags say "Uncensored". The model tree shows ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF as the direct parent with nothing in between.
JonathanColetti/Qwen3.8-27B-Uncensored-GGUFQwen/Qwen3.8-27Bedit-declared-as-quantization Declares itself a quantization of Qwen/Qwen3.8-27B, whose id names no edit, while its own id or tags say "Uncensored". The model tree shows Qwen/Qwen3.8-27B as the direct parent with nothing in between.
OBLITERATUS/Ornith-1.5-9B-OBLITERATEDornith-ai/Ornith-1.5-9Bedit-declared-as-quantization Declares itself a quantization of ornith-ai/Ornith-1.5-9B, whose id names no edit, while its own id or tags say "abliterated". The model tree shows ornith-ai/Ornith-1.5-9B as the direct parent with nothing in between.
OBLITERATUS/Qwen3.8-27B-OBLITERATEDQwen/Qwen3.8-27Bedit-declared-as-quantization Declares itself a quantization of Qwen/Qwen3.8-27B, whose id names no edit, while its own id or tags say "abliterated". The model tree shows Qwen/Qwen3.8-27B as the direct parent with nothing in between.
antirez/qwen3.8-flash-next-ggufQwen/Qwen3.8-Flash-Nextlicence-family-mismatch The declared base Qwen/Qwen3.8-Flash-Next is under other (qwen-community-1.0), and this derivative declares other (qwen-community-license-1.0).
ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUFnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16licence-family-mismatch The declared base nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 is under other (openmdw-1.1), and this derivative declares other.
huihui-ai/Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUFdeepseek-ai/DeepSeek-V4-Flash-0731edit-declared-as-quantization Declares itself a quantization of deepseek-ai/DeepSeek-V4-Flash-0731, whose id names no edit, while its own id or tags say "abliterated". The model tree shows deepseek-ai/DeepSeek-V4-Flash-0731 as the direct parent with nothing in between.
huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUFQwen/Qwen3.6-35B-A3Bedit-declared-as-quantization Declares itself a quantization of Qwen/Qwen3.6-35B-A3B, whose id names no edit, while its own id or tags say "abliterated". The model tree shows Qwen/Qwen3.6-35B-A3B as the direct parent with nothing in between.
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUFQwen/Qwen3.8-27Bedit-declared-as-quantization Declares itself a quantization of Qwen/Qwen3.8-27B, whose id names no edit, while its own id or tags say "abliterated". The model tree shows Qwen/Qwen3.8-27B as the direct parent with nothing in between.
jimmy31chen/RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored-IQ3_S-Strata0bserverx/RVN-Qwen3.8-Flash-Next-Abliterated-Uncensoredlicence-family-mismatch The declared base 0bserverx/RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored is under other (qwen-community-1.0), and this derivative declares apache-2.0.
nvidia/GLM-5.3-NVFP4zai-org/GLM-5.3licence-family-mismatch The declared base zai-org/GLM-5.3 is under other (glm-5.3), and this derivative declares other (nvidia-open-model-license).
nvidia/Kimi-K2-Thinking-NVFP4moonshotai/Kimi-K2-Thinkinglicence-family-mismatch The declared base moonshotai/Kimi-K2-Thinking is under other (modified-mit), and this derivative declares other (nvidia-open-model-license).
nvidia/Kimi-K2.5-NVFP4moonshotai/Kimi-K2.5licence-family-mismatch The declared base moonshotai/Kimi-K2.5 is under other (modified-mit), and this derivative declares other (nvidia-open-model-license).
nvidia/LocateAnything-3BQwen/Qwen2.5-3B-Instructlicence-family-mismatch The declared base Qwen/Qwen2.5-3B-Instruct is under other (qwen-research), and this derivative declares other (nvidia-license).
nvidia/MiniMax-M2.5-NVFP4MiniMaxAI/MiniMax-M2.5licence-family-mismatch The declared base MiniMaxAI/MiniMax-M2.5 is under other (modified-mit), and this derivative declares other (nvidia-open-model-license).
nvidia/MiniMax-M3-NVFP4MiniMaxAI/MiniMax-M3licence-family-mismatch The declared base MiniMaxAI/MiniMax-M3 is under other (minimax-community), and this derivative declares other (minimax-community-license).
nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16nvidia/NVIDIA-Nemotron-Nano-9B-v2licence-family-mismatch The declared base nvidia/NVIDIA-Nemotron-Nano-9B-v2 is under other (nvidia-open-model-license), and this derivative declares other (nvidia-nemotron-open-model-license).
nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16licence-family-mismatch The declared base nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 is under other (nvidia-nemotron-open-model-license), and this derivative declares other (openmdw-1.1).
soyaakinohara/Spark-X2.5-4B-Heretic-jp-ggufXHToken/Spark-X2.5-4Bedit-declared-as-quantization Declares itself a quantization of XHToken/Spark-X2.5-4B, whose id names no edit, while its own id or tags say "Heretic". The model tree shows XHToken/Spark-X2.5-4B as the direct parent with nothing in between.

How this is read

Every day the tracker asks the Hugging Face Hub for the head commit of each tracked model. Only when that commit moved does it read config.json, generation_config.json, tokenizer_config.json, chat_template.jinja and special_tokens_map.json at the new commit, keep a normalised subset of the keys that change what the model computes, how it tokenises, or how it generates by default, and diff it against the last snapshot.

History before the first daily run comes from walking each repository's git history for those files, which is complete for them and blind to the weights: a weight swap with no file change is only visible from the first daily snapshot on.

Chat templates are stored as a sha256 prefix, never in full. Aliases are folded (torch_dtype and dtype, rope_theta inside rope_parameters) so a re-save under a newer transformers is not reported as a change.

A key that differs as stored but not in meaning is kept and labelled format-only, with the fold that equates the two values: RoPE settings rewritten in the transformers v5 rope_parameters form, a tokenizer class and its Fast alias, the library's "unset" sentinel for model_max_length, stop-token ids written as a scalar or a list, and special tokens moved between special_tokens_map.json and tokenizer_config.json. A row whose every key is format-only is a re-save, and it does not count a model as changed.

When a chat template changes, both versions are rendered with @huggingface/jinja on three fixed conversations (system and user, multi-turn, a tool call). Cosmetic means all three rendered byte-identically; that is a statement about those inputs, not a proof the templates are equivalent on every input. The comparison is of rendered text, not token ids: with an unchanged tokenizer the two agree.

Safety-relevant config changes are labelled on the row they belong to: the default system prompt, the tool block, the generation prefix, role validation, a template branch on a non-role literal or a new URL, template code outside the safe Jinja subset, the tokenizer eos_token no longer ending a turn the template writes, and the generation stop list starting or stopping to cover such a token. Each label carries its basis. They are statements about the configuration files and what the renderer printed, never a judgement of how the model behaves; a row without a label was either not read for them or showed nothing, which is not a clean bill.

Licence and access are their own lane: the model card licence field (history recovered from the README's git history), the top-level LICENSE file, and the Hub's gated flag. Gating has no git history, so gating changes exist only from the first daily read on.

Parameter and memory deltas come from reconstructing the graph from each config with the same code the /m/ pages use. Every consequence sentence says what the key does mechanically; none is a report that something broke for anyone.

Pin what you tested

from_pretrained("XiaomiMiMo/MiMo-V2.5", revision="d6bf9db68673d1f903a53d8da417b293fdc97d1f")