33 lines
738 B
JSON
33 lines
738 B
JSON
{
|
|
"architectures": [
|
|
"PhiForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"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": 62.5,
|
|
"type": "dynamic"
|
|
},
|
|
"rope_theta": 50000.0,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.39.3",
|
|
"use_cache": true,
|
|
"vocab_size": 81024
|
|
}
|