Instructions to use mlx-community/MiniMax-M2.7-nvfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/MiniMax-M2.7-nvfp4 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/MiniMax-M2.7-nvfp4") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use mlx-community/MiniMax-M2.7-nvfp4 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "mlx-community/MiniMax-M2.7-nvfp4" --prompt "Once upon a time"
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": "]~!b[", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "[e~[", | |
| "errors": "replace", | |
| "extra_special_tokens": [ | |
| "<code_interpreter>", | |
| "<commit_after>", | |
| "<commit_before>", | |
| "<commit_msg>", | |
| "<empty_output>", | |
| "<filename>", | |
| "<fim_middle>", | |
| "<fim_pad>", | |
| "<fim_prefix>", | |
| "<fim_suffix>", | |
| "<function_call>", | |
| "<gh_stars>", | |
| "]<]speech[>[", | |
| "]<]image[>[", | |
| "]<]video[>[", | |
| "]<]start of speech[>[", | |
| "]<]end of speech[>[", | |
| "]<]start of image[>[", | |
| "]<]end of image[>[", | |
| "]<]start of video[>[", | |
| "]<]end of video[>[", | |
| "]<]vision pad[>[", | |
| "]~!b[", | |
| "<issue_closed>", | |
| "<issue_comment>", | |
| "<issue_start>", | |
| "<jupyter_code>", | |
| "<jupyter_output>", | |
| "<jupyter_start>", | |
| "<jupyter_text>", | |
| "<reponame>", | |
| "[e~[", | |
| "]!d~[", | |
| "]!p~[", | |
| "]~b]", | |
| "<jupyter_error>", | |
| "<add_file>", | |
| "<delete_file>", | |
| "<rename_file>", | |
| "<edit_file>", | |
| "<commit_message>", | |
| "<empty_source_file>", | |
| "<repo_struct>", | |
| "<code_context>", | |
| "<file_content>", | |
| "<source_files>", | |
| "<pr_start>", | |
| "<review_comment>", | |
| "<filepath>", | |
| "<file_sep>" | |
| ], | |
| "is_local": true, | |
| "model_max_length": 40960000, | |
| "pad_token": null, | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "tool_parser_type": "minimax_m2", | |
| "unk_token": "]!d~[" | |
| } | |