Instructions to use AtBeginDocument/Phi-3-mini-4k-instruct-oQ4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AtBeginDocument/Phi-3-mini-4k-instruct-oQ4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Phi-3-mini-4k-instruct-oQ4 AtBeginDocument/Phi-3-mini-4k-instruct-oQ4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "_name_or_path": "Phi-3-mini-4k-instruct", | |
| "architectures": [ | |
| "Phi3ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_phi3.Phi3Config", | |
| "AutoModelForCausalLM": "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, | |
| "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": "4.40.2", | |
| "use_cache": true, | |
| "attention_bias": false, | |
| "vocab_size": 32064, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "model.embed_tokens": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.qkv_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.qkv_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "model.embed_tokens": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.qkv_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.qkv_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.13.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| } | |
| } |