MLX
Safetensors
English
mistral
instruct
finetune
chatml
axolotl
roleplay
mlx-my-repo
4-bit precision
Instructions to use culturerevolt/Codex-24B-Small-3.2-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use culturerevolt/Codex-24B-Small-3.2-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Codex-24B-Small-3.2-mlx-4Bit culturerevolt/Codex-24B-Small-3.2-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "add_prefix_space": null, | |
| "backend": "tokenizers", | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "is_local": true, | |
| "legacy": true, | |
| "model_max_length": 131072, | |
| "pad_token": "<pad>", | |
| "tokenizer_class": "TokenizersBackend", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |