{ "_name_or_path": "./galactica-30b-evol-instruct-70k/", "_remove_final_layer_norm": false, "activation_dropout": 0.0, "activation_function": "gelu", "architectures": [ "OPTForCausalLM" ], "attention_dropout": 0.1, "bos_token_id": 0, "do_layer_norm_before": true, "dropout": 0.1, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 28672, "hidden_size": 7168, "init_std": 0.02, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "learned_embeddings": true, "max_position_embeddings": 2048, "model_type": "opt", "num_attention_heads": 56, "num_hidden_layers": 48, "pad_token_id": 1, "scale_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.29.2", "use_cache": true, "vocab_size": 50000, "word_embed_proj_dim": 7168, "quantization_config": { "bits": 4, "group_size": -1, "damp_percent": 0.01, "desc_act": true, "sym": true, "true_sequential": true, "model_name_or_path": null, "model_file_base_name": "model", "quant_method": "gptq" } }