jerryzh168/phi4-float8dq
07
1{2 "architectures": [3 "Phi3ForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 100257,8 "embd_pdrop": 0.0,9 "eos_token_id": 100265,10 "hidden_act": "silu",11 "hidden_size": 5120,12 "initializer_range": 0.02,13 "intermediate_size": 17920,14 "max_position_embeddings": 16384,15 "model_type": "phi3",16 "num_attention_heads": 40,17 "num_hidden_layers": 40,18 "num_key_value_heads": 10,19 "original_max_position_embeddings": 16384,20 "pad_token_id": 100349,21 "partial_rotary_factor": 1.0,22 "quantization_config": {23 "modules_to_not_convert": null,24 "quant_method": "torchao",25 "quant_type": {26 "default": {27 "_data": {28 "activation_dtype": {29 "_data": "float8_e4m3fn",30 "_type": "torch.dtype"31 },32 "granularity": {33 "_data": {},34 "_type": "PerRow",35 "_version": 136 },37 "mm_config": {38 "_data": {39 "emulate": false,40 "pad_inner_dim": false,41 "use_fast_accum": true42 },43 "_type": "Float8MMConfig",44 "_version": 145 },46 "set_inductor_config": true,47 "weight_dtype": {48 "_data": "float8_e4m3fn",49 "_type": "torch.dtype"50 }51 },52 "_type": "Float8DynamicActivationFloat8WeightConfig",53 "_version": 154 }55 },56 "quant_type_kwargs": {}57 },58 "resid_pdrop": 0.0,59 "rms_norm_eps": 1e-05,60 "rope_scaling": null,61 "rope_theta": 250000,62 "sliding_window": null,63 "tie_word_embeddings": false,64 "torch_dtype": "bfloat16",65 "transformers_version": "4.51.0.dev0",66 "use_cache": true,67 "vocab_size": 10035268}69 