Changes / Feeds / unsloth/Llama-3.2-1B-Instruct
unsloth/Llama-3.2-1B-Instruct
6 changes to a tracked key since 2024-09-25, newest first. Head as last read: 5a8abab4a5d6f164389b1079fb721cfab8d7126c.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-02-25 | x_NXMC-2025-0108 breaking | tokenizer_class "PreTrainedTokenizerFast" to "PreTrainedTokenizer" (2025-02-25).eb49081324ed -> 9b58d4a36161 |
| 2025-01-23 | x_NXMC-2025-0107 breaking | EOS changed from [128001,128008,128009] to 128009; anything fine-tuned or served against the old value stops at a different token (2025-01-23).2906abdacc8c -> eb49081324ed |
| 2025-01-22 | x_NXMC-2025-0106 breaking | 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 (2025-01-22).0430e7102ae7 -> 2906abdacc8c |
| 2025-01-22 | x_NXMC-2025-0105 breaking | pad token unset to 128004; batched training masks a different 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; add_bos_token unset to true; encoding the same text yields different ids (2025-01-22).bd6d97814a86 -> 0430e7102ae7 |
| 2024-09-29 | x_NXMC-2024-0109 | pad token unset to "<|finetune_right_pad_id|>"; batched training masks a different id (2024-09-29).d5a34d2d81ec -> bd6d97814a86 |
| 2024-09-29 | x_NXMC-2024-0108 | pad token "<|finetune_right_pad_id|>" to unset; batched training masks a different id (2024-09-29).4e20426873bd -> d5a34d2d81ec |
Pin it, and let a bot move the pin
from_pretrained("unsloth/Llama-3.2-1B-Instruct", revision="5a8abab4a5d6f164389b1079fb721cfab8d7126c")With the Renovate preset, a pull request moves this pin when the head moves, and links back here.
[](https://www.neurarch.com/changes-feeds/models/unsloth/Llama-3.2-1B-Instruct.html)