Changes / Feeds / ai-sage/Giga-Embeddings-instruct
ai-sage/Giga-Embeddings-instruct
5 changes to a tracked key since 2024-12-12, newest first. Head as last read: 2cf0fdc97194aaedf10ac0e6bf798834acd31042.
GPU memory to fine-tune it, card by card: Giga-Embeddings-instruct on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-09-23 | x_NXMC-2025-0021 breaking | model_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).b3dc287fece8 -> 3c12a846f3f9 |
| 2025-09-23 | x_NXMC-2025-0020 breaking | head 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).f4891741cf49 -> b3dc287fece8 |
| 2025-06-04 | x_NXMC-2025-0019 breaking | context window 32768 to 4096 tokens (2025-06-04).0cd92734c456 -> f4891741cf49 |
| 2025-05-29 | x_NXMC-2025-0018 breaking | layer count 27 to 36; derived parameters 2.61B to 3.30B (+693.7M, +1.39 GB of bf16 weights) (2025-05-29).201baa9d6f8f -> e5a07187e0d1 |
| 2024-12-19 | x_NXMC-2024-0014 | pad token unset to "<unk>"; batched training masks a different id (2024-12-19).b2c9c67d18d6 -> 201baa9d6f8f |
Pin it, and let a bot move the pin
from_pretrained("ai-sage/Giga-Embeddings-instruct", revision="2cf0fdc97194aaedf10ac0e6bf798834acd31042")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/ai-sage/Giga-Embeddings-instruct.html)