Instructions to use RESMP-DEV/LFM2.5-Encoder-350M-Code-MXFP8-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use RESMP-DEV/LFM2.5-Encoder-350M-Code-MXFP8-GPTQ with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir LFM2.5-Encoder-350M-Code-MXFP8-GPTQ RESMP-DEV/LFM2.5-Encoder-350M-Code-MXFP8-GPTQ
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| # Modifications by RESMP.DEV | |
| This is a derivative of the identified LiquidAI LFM2.5 Encoder checkpoint, not an official LiquidAI release. RESMP.DEV removed the masked-language-model head and contrastively fine-tuned the complete encoder body for code retrieval using the procedure and corpus hashes in `training_report.json`. The resulting weights are stored in BF16. | |
| RESMP.DEV activation-calibrated the BF16 weights with block-GPTQ and packed eligible linear layers as native group-32 MLX MXFP8. Exact settings and hashes are recorded in `quantization_report.json`. | |