Instructions to use brainworkup/LFM2.5-8B-A1B-oQ8e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use brainworkup/LFM2.5-8B-A1B-oQ8e with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir LFM2.5-8B-A1B-oQ8e brainworkup/LFM2.5-8B-A1B-oQ8e
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 124894, | |
| "eos_token_id": 124900, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": 124893, | |
| "do_sample": true, | |
| "temperature": 0.2, | |
| "top_k": 80, | |
| "repetition_penalty": 1.05, | |
| "transformers_version": "5.9.0", | |
| "use_cache": true | |
| } | |