phi4-float8dq / config.json
jerryzh168's picture
Upload Phi3ForCausalLM
63e59af verified
{
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 100257,
"embd_pdrop": 0.0,
"eos_token_id": 100265,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 17920,
"max_position_embeddings": 16384,
"model_type": "phi3",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 10,
"original_max_position_embeddings": 16384,
"pad_token_id": 100349,
"partial_rotary_factor": 1.0,
"quantization_config": {
"modules_to_not_convert": null,
"quant_method": "torchao",
"quant_type": {
"default": {
"_data": {
"activation_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
},
"granularity": {
"_data": {},
"_type": "PerRow",
"_version": 1
},
"mm_config": {
"_data": {
"emulate": false,
"pad_inner_dim": false,
"use_fast_accum": true
},
"_type": "Float8MMConfig",
"_version": 1
},
"set_inductor_config": true,
"weight_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
}
},
"_type": "Float8DynamicActivationFloat8WeightConfig",
"_version": 1
}
},
"quant_type_kwargs": {}
},
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 250000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0.dev0",
"use_cache": true,
"vocab_size": 100352
}