Instructions to use carlmuck/Star-Command-R-32B-v1-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use carlmuck/Star-Command-R-32B-v1-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download carlmuck/Star-Command-R-32B-v1-mlx-4Bit --local-dir Star-Command-R-32B-v1-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download tokenizer_config.json from carlmuck/Star-Command-R-32B-v1-mlx-4Bit: direct link, hf CLI and curl.
- Browser
- Download file 556 Bytes
-
https://huggingface.co/carlmuck/Star-Command-R-32B-v1-mlx-4Bit/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://carlmuck/Star-Command-R-32B-v1-mlx-4Bit/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/carlmuck/Star-Command-R-32B-v1-mlx-4Bit/resolve/main/tokenizer_config.json
556 Bytes
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": "<BOS_TOKEN>", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "<CLS>", | |
| "eos_token": "<|END_OF_TURN_TOKEN|>", | |
| "errors": "replace", | |
| "is_local": true, | |
| "legacy": true, | |
| "mask_token": "<MASK_TOKEN>", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<PAD>", | |
| "sep_token": "<SEP>", | |
| "sp_model_kwargs": {}, | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "CohereTokenizer", | |
| "unk_token": null, | |
| "use_default_system_prompt": false | |
| } | |