Downloads · 30 days
26
5% of all-time downloads
LFM2.5-1.2B-Instruct-Autoround-Safetensors
simaai/LFM2.5-1.2B-Instruct-Autoround-Safetensors
LFM2.5-1.2B-Instruct-Autoround-Safetensors is a text generation model from simaai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
Pre-LLiMa Hugging Face checkpoint based on LiquidAI/LFM2.5-1.2B-Instruct at source revision 6314d2b7cf28a6ae9de9d3e77dcfcd9c9f281c77. It remains subject to the base model's license, intended use, and limitations.
All-time downloads
575
Public
Parameters
1.3B
1.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors863 MB · 99%
Parameter types
How the weights are stored.
I321.2B · 90%
Base models
Model card
From the Hugging Face model README
LFM2.5-1.2B-Instruct Autoround
Pre-LLiMa Hugging Face checkpoint based on LiquidAI/LFM2.5-1.2B-Instruct at source revision 6314d2b7cf28a6ae9de9d3e77dcfcd9c9f281c77. It remains subject to the base model's license, intended use, and limitations.
Quantization
| Component | Method | Weight format | Details |
|---|---|---|---|
| Decoder Linear layers | AutoRound | symmetric INT4, G256 | 92 targets; lm_head excluded |
lm_head | GPTQ | symmetric INT4, G256 | static act-order, block size 128, dampening 0.01 |
| Mixed-precision exceptions | — | source dtype | non-Linear parameters remain at source precision |
Calibration used HuggingFaceH4/ultrachat_200k, train_sft[:512], rendered with the source chat template. Token IDs were deterministically concatenated and packed into 512 full 1024-token spans (no shuffle); AutoRound used 200 iterations and batch size 1.
Evaluation
Full wikitext-2-raw-v1 evaluation used the wikitext lm-eval task, no example limit, batch size 1, CUDA, and the same evaluator for source and quantized checkpoints on 2026-07-19.
| Checkpoint | Word perplexity | Status |
|---|---|---|
LiquidAI/LFM2.5-1.2B-Instruct source | 33.871271 | Full run |
| This UltraChat checkpoint | 42.956951 | Full run |
| Absolute degradation | 9.085681 | Lower is better |
| Relative degradation | 26.824% | 100 * (quantized / source - 1) |
UltraChat is the selected calibration corpus because the intended deployment prioritizes instruction-following data. Finite-scale validation and a Transformers chat-generation smoke test passed.
Reproduction
This directory includes the exact quantize.py, recipe.yaml, and versions.txt.
python quantize.py --model-path /path/to/models--LiquidAI--LFM2.5-1.2B-Instruct --output-dir /path/to/output
Environment
Exact Python, CUDA, Torch, Transformers, llm-compressor, AutoRound, and
compressed-tensors versions are recorded in versions.txt.
Deployment
This is the pre-LLiMa quantized Hugging Face artifact. Compile it separately for the target Sima.ai platform and keep compiler output separate. No upload is authorized as part of the current local batch.
Limitations
WikiText perplexity does not directly measure instruction following. Quantization quality can vary by language, domain, prompt format, context length, safety requirements, and deployment runtime; validate the intended workload independently.
- Task
- Text Generation
- Library
- transformers
- Type
- lfm2
- License
- mit
- Languages
- multilingual
- Created
- Jul 16, 2026
- Updated
- Sep 1, 2026