23 lines
492 B
JSON
23 lines
492 B
JSON
|
{
|
||
|
|
"architectures": ["GPT2LMHeadModel"],
|
||
|
|
"model_type": "gpt2",
|
||
|
|
"vocab_size": 50257,
|
||
|
|
"n_embd": 2048,
|
||
|
|
"n_head": 16,
|
||
|
|
"n_inner": 8192,
|
||
|
|
"n_layer": 38,
|
||
|
|
"n_positions": 2048,
|
||
|
|
"n_ctx": 2048,
|
||
|
|
"bos_token_id": 50256,
|
||
|
|
"eos_token_id": 50256,
|
||
|
|
"activation_function": "gelu_new",
|
||
|
|
"attn_pdrop": 0.0,
|
||
|
|
"embd_pdrop": 0.0,
|
||
|
|
"resid_pdrop": 0.0,
|
||
|
|
"layer_norm_epsilon": 1e-05,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"use_cache": true,
|
||
|
|
"tie_word_embeddings": true
|
||
|
|
}
|