You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit a398a96
Browse filesBrowse the repository at this point in the historyBrowse files
Add LFM2.5 1.2B support with CI integration (pytorch#17509)
This adds support for exporting LiquidAI's LFM2.5-1.2B-Instruct model,
which features improved training (28T tokens vs 10T) and extended
context support (32K tokens).
Changes:
- Add lfm2_5_1_2b model configuration
(examples/models/lfm2/config/lfm2_5_1_2b_config.json)
- Register lfm2_5_1_2b in EXECUTORCH_DEFINED_MODELS and
HUGGING_FACE_REPO_IDS
- Add lfm2_5_1_2b to ModelType enum
- Update README with LFM2.5 export examples and extended context usage
- Add CI test for lfm2_5_1_2b in test_torchao_huggingface_checkpoints.sh
- Add lfm2_5_1_2b to trunk.yml test matrix (XNNPACK and TorchAO
backends)
The model uses the same hybrid architecture as LFM2 (convolution +
attention layers) with 16 layers and 8192 FFN dimension. Can be exported
with custom max_seq_length and max_context_length for extended context
support.
Fixespytorch#17439
---------
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Copy file name to clipboardExpand all lines: examples/models/lfm2/README.md
+22Lines changed: 22 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,8 @@
1
1
## Summary
2
2
[LFM2](https://huggingface.co/collections/LiquidAI/lfm2-686d721927015b2ad73eaa38) is a new generation of hybrid models developed by [Liquid AI](https://www.liquid.ai/) and available in 3 variants - 350M, 700M, 1.2B.
3
3
4
+
[LFM2.5](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) is an updated version with improved training (28T tokens vs 10T) and extended context length support (32K tokens).
5
+
4
6
## Instructions
5
7
6
8
LFM2 uses the same example code as optimized Llama model, while the checkpoint, model params, and tokenizer are different. Please see the [Llama README page](../llama/README.md) for details.
0 commit comments