bapatra's picture
Add attention_bias to make TGI work (#2)
9b3142d verified
{
"_name_or_path": "Phi-3-medium-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": 5120,
"initializer_range": 0.02,
"intermediate_size": 17920,
"max_position_embeddings": 4096,
"model_type": "phi3",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 10,
"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": "4.39.3",
"use_cache": true,
"attention_bias": false,
"vocab_size": 32064
}