Instructions to use baa-ai/Llama-4-Maverick-17B-128E-Instruct-RAM-170GB-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use baa-ai/Llama-4-Maverick-17B-128E-Instruct-RAM-170GB-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Llama-4-Maverick-17B-128E-Instruct-RAM-170GB-MLX baa-ai/Llama-4-Maverick-17B-128E-Instruct-RAM-170GB-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "backend": "tokenizers", | |
| "bos_token": "<|begin_of_text|>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|eot|>", | |
| "is_local": true, | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 1048576, | |
| "pad_token": "<|finetune_right_pad|>", | |
| "processor_class": "Llama4Processor", | |
| "tokenizer_class": "TokenizersBackend" | |
| } | |