3f879ff35d
- Add EOS token (ec7094f5d65a66ec033c08f90729f72f2603e2a1) Co-authored-by: Joao Gante <joaogante@users.noreply.huggingface.co>
35 lines
863 B
JSON
35 lines
863 B
JSON
{
|
|
"_name_or_path": "microsoft/phi-2",
|
|
"architectures": [
|
|
"PhiForCausalLM"
|
|
],
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_phi.PhiConfig",
|
|
"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
|
|
},
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 50256,
|
|
"embd_pdrop": 0.0,
|
|
"eos_token_id": 50256,
|
|
"hidden_act": "gelu_new",
|
|
"hidden_size": 2560,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 10240,
|
|
"layer_norm_eps": 1e-05,
|
|
"max_position_embeddings": 2048,
|
|
"model_type": "phi",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 32,
|
|
"partial_rotary_factor": 0.4,
|
|
"qk_layernorm": false,
|
|
"resid_pdrop": 0.1,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000.0,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.37.0",
|
|
"use_cache": true,
|
|
"vocab_size": 51200
|
|
}
|