MLX
Safetensors
English
llama
obliteratus
abliteration
uncensored
obliterate
mlx-my-repo
4-bit precision
Instructions to use usermma/AMALIA-9B-0626-SFT-Heretic-Abliterated-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use usermma/AMALIA-9B-0626-SFT-Heretic-Abliterated-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir AMALIA-9B-0626-SFT-Heretic-Abliterated-mlx-4Bit usermma/AMALIA-9B-0626-SFT-Heretic-Abliterated-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "add_prefix_space": true, | |
| "backend": "tokenizers", | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "max_length": 64, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_to_multiple_of": null, | |
| "pad_token": "</s>", | |
| "pad_token_type_id": 0, | |
| "padding_side": "left", | |
| "sp_model_kwargs": {}, | |
| "spaces_between_special_tokens": false, | |
| "stride": 0, | |
| "tokenizer_class": "LlamaTokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |