{ "_name_or_path": "microsoft/Phi-3-mini-4k-instruct", "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "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_config": { "config_groups": {}, "format": "dense", "global_compression_ratio": 1.0, "ignore": [ "model.layers.0.self_attn.o_proj", "model.layers.0.self_attn.qkv_proj", "model.layers.0.mlp.gate_up_proj", "model.layers.0.mlp.down_proj", "model.layers.1.self_attn.o_proj", "model.layers.1.self_attn.qkv_proj", "model.layers.1.mlp.gate_up_proj", "model.layers.1.mlp.down_proj", "model.layers.2.self_attn.o_proj", "model.layers.2.self_attn.qkv_proj", "model.layers.2.mlp.gate_up_proj", "model.layers.2.mlp.down_proj", "model.layers.3.self_attn.o_proj", "model.layers.3.self_attn.qkv_proj", "model.layers.3.mlp.gate_up_proj", "model.layers.3.mlp.down_proj", "model.layers.4.self_attn.o_proj", "model.layers.4.self_attn.qkv_proj", "model.layers.4.mlp.gate_up_proj", "model.layers.4.mlp.down_proj", "model.layers.5.self_attn.o_proj", "model.layers.5.self_attn.qkv_proj", "model.layers.5.mlp.gate_up_proj", "model.layers.5.mlp.down_proj", "model.layers.6.self_attn.o_proj", "model.layers.6.self_attn.qkv_proj", "model.layers.6.mlp.gate_up_proj", "model.layers.6.mlp.down_proj", "model.layers.7.self_attn.o_proj", "model.layers.7.self_attn.qkv_proj", "model.layers.7.mlp.gate_up_proj", "model.layers.7.mlp.down_proj", "model.layers.8.self_attn.o_proj", "model.layers.8.self_attn.qkv_proj", "model.layers.8.mlp.gate_up_proj", "model.layers.8.mlp.down_proj", "model.layers.9.self_attn.o_proj", "model.layers.9.self_attn.qkv_proj", "model.layers.9.mlp.gate_up_proj", "model.layers.9.mlp.down_proj", "model.layers.10.self_attn.o_proj", "model.layers.10.self_attn.qkv_proj", "model.layers.10.mlp.gate_up_proj", "model.layers.10.mlp.down_proj", "model.layers.11.self_attn.o_proj", "model.layers.11.self_attn.qkv_proj", "model.layers.11.mlp.gate_up_proj", "model.layers.11.mlp.down_proj", "model.layers.12.self_attn.o_proj", "model.layers.12.self_attn.qkv_proj", "model.layers.12.mlp.gate_up_proj", "model.layers.12.mlp.down_proj", "model.layers.13.self_attn.o_proj", "model.layers.13.self_attn.qkv_proj", "model.layers.13.mlp.gate_up_proj", "model.layers.13.mlp.down_proj", "model.layers.14.self_attn.o_proj", "model.layers.14.self_attn.qkv_proj", "model.layers.14.mlp.gate_up_proj", "model.layers.14.mlp.down_proj", "model.layers.15.self_attn.o_proj", "model.layers.15.self_attn.qkv_proj", "model.layers.15.mlp.gate_up_proj", "model.layers.15.mlp.down_proj", "model.layers.16.self_attn.o_proj", "model.layers.16.self_attn.qkv_proj", "model.layers.16.mlp.gate_up_proj", "model.layers.16.mlp.down_proj", "model.layers.17.self_attn.o_proj", "model.layers.17.self_attn.qkv_proj", "model.layers.17.mlp.gate_up_proj", "model.layers.17.mlp.down_proj", "model.layers.18.self_attn.o_proj", "model.layers.18.self_attn.qkv_proj", "model.layers.18.mlp.gate_up_proj", "model.layers.18.mlp.down_proj", "model.layers.19.self_attn.o_proj", "model.layers.19.self_attn.qkv_proj", "model.layers.19.mlp.gate_up_proj", "model.layers.19.mlp.down_proj", "model.layers.20.self_attn.o_proj", "model.layers.20.self_attn.qkv_proj", "model.layers.20.mlp.gate_up_proj", "model.layers.20.mlp.down_proj", "model.layers.21.self_attn.o_proj", "model.layers.21.self_attn.qkv_proj", "model.layers.21.mlp.gate_up_proj", "model.layers.21.mlp.down_proj", "model.layers.22.self_attn.o_proj", "model.layers.22.self_attn.qkv_proj", "model.layers.22.mlp.gate_up_proj", "model.layers.22.mlp.down_proj", "model.layers.23.self_attn.o_proj", "model.layers.23.self_attn.qkv_proj", "model.layers.23.mlp.gate_up_proj", "model.layers.23.mlp.down_proj", "model.layers.24.self_attn.o_proj", "model.layers.24.self_attn.qkv_proj", "model.layers.24.mlp.gate_up_proj", "model.layers.24.mlp.down_proj", "model.layers.25.self_attn.o_proj", "model.layers.25.self_attn.qkv_proj", "model.layers.25.mlp.gate_up_proj", "model.layers.25.mlp.down_proj", "model.layers.26.self_attn.o_proj", "model.layers.26.self_attn.qkv_proj", "model.layers.26.mlp.gate_up_proj", "model.layers.26.mlp.down_proj", "model.layers.27.self_attn.o_proj", "model.layers.27.self_attn.qkv_proj", "model.layers.27.mlp.gate_up_proj", "model.layers.27.mlp.down_proj", "model.layers.28.self_attn.o_proj", "model.layers.28.self_attn.qkv_proj", "model.layers.28.mlp.gate_up_proj", "model.layers.28.mlp.down_proj", "model.layers.29.self_attn.o_proj", "model.layers.29.self_attn.qkv_proj", "model.layers.29.mlp.gate_up_proj", "model.layers.29.mlp.down_proj", "model.layers.30.self_attn.o_proj", "model.layers.30.self_attn.qkv_proj", "model.layers.30.mlp.gate_up_proj", "model.layers.30.mlp.down_proj", "model.layers.31.self_attn.o_proj", "model.layers.31.self_attn.qkv_proj", "model.layers.31.mlp.gate_up_proj", "model.layers.31.mlp.down_proj", "lm_head" ], "kv_cache_scheme": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "minmax", "observer_kwargs": {}, "strategy": "tensor", "symmetric": true, "type": "float" }, "quant_method": "compressed-tensors", "quantization_status": "frozen" }, "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": "4.47.1", "use_cache": true, "vocab_size": 32064 }