{ | |
"model_type": "gpt2", | |
"vocab_size": 50257, | |
"n_positions": 1024, | |
"n_ctx": 1024, | |
"n_embd": 768, | |
"n_layer": 12, | |
"n_head": 12, | |
"resid_pdrop": 0.1, | |
"embd_pdrop": 0.1, | |
"attn_pdrop": 0.1, | |
"layer_norm_epsilon": 1e-05, | |
"initializer_range": 0.02, | |
"output_attentions": false, | |
"output_hidden_states": false, | |
"use_cache": true | |
} | |