27 lines
578 B
JSON
27 lines
578 B
JSON
{
|
|
"activation_function": "gelu_fast",
|
|
"architectures": [
|
|
"GPT2LMHeadModel"
|
|
],
|
|
"attn_pdrop": 0.1,
|
|
"bos_token_id": 2,
|
|
"embd_pdrop": 0.1,
|
|
"eos_token_id": 3,
|
|
"gradient_checkpointing": false,
|
|
"initializer_range": 0.02,
|
|
"layer_norm_epsilon": 1e-05,
|
|
"model_type": "gpt2",
|
|
"n_ctx": 1024,
|
|
"n_embd": 2048,
|
|
"n_head": 16,
|
|
"n_inner": 8192,
|
|
"n_layer": 24,
|
|
"n_positions": 1024,
|
|
"reorder_and_upcast_attn": false,
|
|
"resid_pdrop": 0.1,
|
|
"scale_attn_by_inverse_layer_idx": false,
|
|
"scale_attn_weights": true,
|
|
"use_cache": true,
|
|
"vocab_size": 44928
|
|
}
|