{ "_name_or_path": "facebook/opt-13b", "_remove_final_layer_norm": false, "activation_dropout": 0.0, "activation_function": "relu", "antemplate": "[Genre: <|>]", "architectures": [ "OPTForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 2, "do_layer_norm_before": true, "dropout": 0.1, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 20480, "hidden_size": 5120, "init_std": 0.02, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 2048, "model_type": "opt", "num_attention_heads": 40, "num_hidden_layers": 40, "output_projection": true, "pad_token_id": 1, "prefix": "", "torch_dtype": "float16", "transformers_version": "4.25.1", "use_cache": false, "vocab_size": 50265, "welcome": "## Warning: This model has a very heavy NSFW bias and is not suitable for use by minors!\n\nYou are currently running the model `OPT-13B-Nerybus-Mix.`\n\nThis is an experimental model containing a parameter-wise 50/50 blend (weighted average) of NerysV2-13B and ErebusV1-13B.\n\n", "word_embed_proj_dim": 5120 }