| { | |
| "activation_dropout": 0.0, | |
| "activation_function": "relu", | |
| "architectures": [ | |
| "OPTModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "d_model": 4096, | |
| "decoder_layernorm": false, | |
| "decoder_start_token_id": 2, | |
| "dropout": 0.1, | |
| "eos_token_id": 2, | |
| "ffn_dim": 16384, | |
| "init_std": 0.02, | |
| "layerdrop": 0.0, | |
| "max_position_embeddings": 2048, | |
| "model_type": "opt", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "output_projection": true, | |
| "pad_token_id": 1, | |
| "scale_embedding": false, | |
| "share_input_output_embed": true, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.19.0.dev0", | |
| "use_cache": false, | |
| "vocab_size": 50272, | |
| "word_embed_proj_dim": 4096, | |
| "_remove_final_layer_norm": true | |
| } |