33 lines
844 B
JSON
33 lines
844 B
JSON
{
|
|
"_name_or_path": "/home/gderosa/.cache/huggingface/hub/models--mojanjp--phi2/snapshots/e74b3704fed862c23190b41c5756f4c22dd461b7",
|
|
"activation_function": "gelu_new",
|
|
"architectures": [
|
|
"PhiForCausalLM"
|
|
],
|
|
"attn_pdrop": 0.0,
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_phi.PhiConfig",
|
|
"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
|
|
},
|
|
"embd_pdrop": 0.0,
|
|
"flash_attn": false,
|
|
"flash_rotary": false,
|
|
"fused_dense": false,
|
|
"img_processor": null,
|
|
"initializer_range": 0.02,
|
|
"layer_norm_epsilon": 1e-05,
|
|
"model_type": "phi",
|
|
"n_embd": 2560,
|
|
"n_head": 32,
|
|
"n_head_kv": null,
|
|
"n_inner": null,
|
|
"n_layer": 32,
|
|
"n_positions": 2048,
|
|
"resid_pdrop": 0.1,
|
|
"rotary_dim": 32,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.35.2",
|
|
"vocab_size": 51200
|
|
}
|