38 lines
951 B
JSON
38 lines
951 B
JSON
|
{
|
||
|
|
"_name_or_path": "voidful/phi-1_5_base",
|
||
|
|
"architectures": [
|
||
|
|
"PhiForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"auto_map": {
|
||
|
|
"AutoConfig": "microsoft/phi-1_5--configuration_phi.PhiConfig",
|
||
|
|
"AutoModelForCausalLM": "microsoft/phi-1_5--modeling_phi.PhiForCausalLM"
|
||
|
|
},
|
||
|
|
"bos_token_id": null,
|
||
|
|
"embd_pdrop": 0.0,
|
||
|
|
"eos_token_id": null,
|
||
|
|
"hidden_act": "gelu_new",
|
||
|
|
"hidden_size": 2048,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 8192,
|
||
|
|
"layer_norm_eps": 1e-05,
|
||
|
|
"max_position_embeddings": 2048,
|
||
|
|
"model_type": "phi",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 24,
|
||
|
|
"num_key_value_heads": 32,
|
||
|
|
"partial_rotary_factor": 0.5,
|
||
|
|
"qk_layernorm": false,
|
||
|
|
"resid_pdrop": 0.0,
|
||
|
|
"rope_scaling": {
|
||
|
|
"factor": 16.0,
|
||
|
|
"type": "dynamic"
|
||
|
|
},
|
||
|
|
"rope_theta": 50000.0,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.40.0.dev0",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 80980
|
||
|
|
}
|