35 lines
716 B
JSON
35 lines
716 B
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"GPT2LMHeadModel"
|
||
|
|
],
|
||
|
|
"model_type": "gpt2",
|
||
|
|
"vocab_size": 50002,
|
||
|
|
"n_positions": 1024,
|
||
|
|
"n_ctx": 1024,
|
||
|
|
"n_embd": 768,
|
||
|
|
"n_layer": 12,
|
||
|
|
"n_head": 12,
|
||
|
|
"n_inner": 3072,
|
||
|
|
"activation_function": "gelu_new",
|
||
|
|
"resid_pdrop": 0.0,
|
||
|
|
"embd_pdrop": 0.0,
|
||
|
|
"attn_pdrop": 0.0,
|
||
|
|
"layer_norm_epsilon": 1e-05,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"use_cache": true,
|
||
|
|
"bos_token_id": 0,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"transformers_version": "4.0.0",
|
||
|
|
"_name_or_path": "riken-gpt2",
|
||
|
|
"_riken_model_args": {
|
||
|
|
"n_layer": 12,
|
||
|
|
"n_head": 12,
|
||
|
|
"n_embd": 768,
|
||
|
|
"block_size": 1024,
|
||
|
|
"bias": false,
|
||
|
|
"vocab_size": 50257,
|
||
|
|
"dropout": 0.0
|
||
|
|
},
|
||
|
|
"_riken_bias": false,
|
||
|
|
"pad_token_id": 0
|
||
|
|
}
|