Instructions to use taontronic/NPC-LLM-3_8B-mlx-8Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use taontronic/NPC-LLM-3_8B-mlx-8Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir NPC-LLM-3_8B-mlx-8Bit taontronic/NPC-LLM-3_8B-mlx-8Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "architectures": [ | |
| "Phi3ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", | |
| "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 32000, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 4096, | |
| "model_type": "phi3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "original_max_position_embeddings": 4096, | |
| "pad_token_id": 32000, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "resid_pdrop": 0.0, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 2047, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.38.1", | |
| "use_cache": true, | |
| "vocab_size": 32064 | |
| } |