Downloads · 30 days
38
7% of all-time downloads
LFM2-2.6B-Autoround-Safetensors
simaai/LFM2-2.6B-Autoround-Safetensors
LFM2-2.6B-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.
Post-training quantized LiquidAI/LFM2-2.6B, prepared as a pre-LLiMa Hugging Face checkpoint for Sima.ai. The immutable source revision was not captured in the local cache and must be pinned before any publication.
All-time downloads
560
Public
Parameters
2.7B
1.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 100%
Parameter types
How the weights are stored.
I322.6B · 95%
Try a prompt
Base models
Model card
From the Hugging Face model README
LFM2-2.6B Autoround Safetensors
Post-training quantized LiquidAI/LFM2-2.6B, prepared as a pre-LLiMa Hugging Face checkpoint for Sima.ai. The immutable source revision was not captured in the local cache and must be pinned before any publication.
Quantization
| Component | Method | Format | Details |
|---|---|---|---|
| All decoder Linear weights | AutoRound | symmetric INT4, G256 | 166 modules including short-convolution projection Linear layers; lm_head excluded; W4A16 |
lm_head | GPTQ | symmetric INT4, G256 | static actorder; block size 128; dampening 0.01 |
| Convolution kernels and activations | — | FP16/BF16 | not quantized |
Calibration used 512 fixed-order samples from NeelNanda/pile-10k, sequence length 1024, AutoRound 200 iterations, batch size 1, and device ID 0.
Evaluation
Full wikitext-2-raw-v1 was evaluated through lm-eval's wikitext task with no example limit and matched settings for both checkpoints.
| Checkpoint | Word perplexity | Status |
|---|---|---|
LiquidAI/LFM2-2.6B | 28.261791339221 | Full run: 2026-07-15 |
| This checkpoint | 29.264924001060 | Full run: 2026-07-15 |
| Absolute degradation | +1.003132661839 | quantized - source |
| Relative degradation | +3.549430571470% | 100 * (quantized / source - 1) |
Raw JSON evidence is retained in perplexity_results/full_wikitext/ in this workspace.
Reproduction
Included files: README.md, quantize.py, recipe.yaml, and versions.txt.
python quantize.py --model-path /path/to/LFM2-2.6B --output-dir /path/to/new-output-directory
The quantization job completed on an NVIDIA A100 80 GB GPU on 2026-07-15 and saved scales passed the NaN/Inf check. The compressed-checkpoint smoke test passed: 167 compressed modules including lm_head loaded and completed greedy generation.
Deployment and limitations
This is a pre-LLiMa quantized Hugging Face safetensors artifact. Compile separately for Sima.ai with the appropriate LLiMa release. Quantization quality can vary by language, domain, prompt format, and context length; validate your deployment.
- Task
- Text Generation
- Library
- transformers
- Type
- lfm2
- License
- mit
- Created
- Jul 16, 2026
- Updated
- Sep 1, 2026