36 lines
880 B
JSON
36 lines
880 B
JSON
{
|
|
"_name_or_path": "phi-1.5-half",
|
|
"activation_function": "gelu_new",
|
|
"architecture": {
|
|
"block_cls": "parallel",
|
|
"mixer": {},
|
|
"mlp": {
|
|
"mlp_cls": "mlp"
|
|
}
|
|
},
|
|
"architectures": [
|
|
"MixFormerSequentialForCausalLM"
|
|
],
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_mixformer_sequential.MixFormerSequentialConfig",
|
|
"AutoModelForCausalLM": "modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
|
|
},
|
|
"embd_layer": "default",
|
|
"embd_pdrop": 0.0,
|
|
"initializer_range": 0.02,
|
|
"layer_norm_epsilon": 1e-05,
|
|
"model_type": "mixformer-sequential",
|
|
"n_embd": 2048,
|
|
"n_head": 32,
|
|
"n_inner": null,
|
|
"n_layer": 24,
|
|
"n_positions": 2048,
|
|
"phyagi_version": "0.0.4.dev",
|
|
"resid_pdrop": 0.0,
|
|
"rotary_dim": 32,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.32.1",
|
|
"vocab_size": 51200
|
|
}
|