MLX
Safetensors
English
gpt_oss
lora
muon
apple-silicon
Mixture of Experts
coding
agent
fine-tuned
4-bit precision
Instructions to use cloudyu/gpt-oss-120b-Fable-5-Distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use cloudyu/gpt-oss-120b-Fable-5-Distilled with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gpt-oss-120b-Fable-5-Distilled cloudyu/gpt-oss-120b-Fable-5-Distilled
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "bos_token_id": 199998, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 200002, | |
| 199999, | |
| 200012 | |
| ], | |
| "pad_token_id": 199999, | |
| "transformers_version": "4.57.1" | |
| } | |