{ | |
"model_type": "gpt2", | |
"vocab_size": 50257, | |
"n_positions": 2048, | |
"n_ctx": 2048, | |
"n_embd": 2560, | |
"n_layer": 24, | |
"n_head": 32, | |
"resid_pdrop": 0.1, | |
"embd_pdrop": 0.1, | |
"attn_pdrop": 0.1, | |
"layer_norm_epsilon": 1e-5 | |
} | |
{ | |
"model_type": "gpt2", | |
"vocab_size": 50257, | |
"n_positions": 2048, | |
"n_ctx": 2048, | |
"n_embd": 2560, | |
"n_layer": 24, | |
"n_head": 32, | |
"resid_pdrop": 0.1, | |
"embd_pdrop": 0.1, | |
"attn_pdrop": 0.1, | |
"layer_norm_epsilon": 1e-5 | |
} | |