{ "_name_or_path": "EleutherAI/gpt-neo-2.7B", "activation_function": "gelu_new", "architectures": [ "GPTNeoForCausalLM" ], "attention_dropout": 0, "attention_layers": [ "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local" ], "attention_types": [ [ [ "global", "local" ], 16 ] ], "bos_token_id": 50256, "classifier_dropout": 0.1, "embed_dropout": 0, "eos_token_id": 50256, "gradient_checkpointing": false, "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": null, "layer_norm_epsilon": 1e-05, "max_position_embeddings": 2048, "model_type": "gpt_neo", "num_heads": 20, "num_layers": 32, "pretraining_tp": 1, "quantization_config": { "_load_in_4bit": false, "_load_in_8bit": true, "bnb_4bit_compute_dtype": "float32", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "fp4", "bnb_4bit_use_double_quant": false, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": null, "llm_int8_threshold": 6.0, "load_in_4bit": false, "load_in_8bit": true, "quant_method": "bitsandbytes" }, "resid_dropout": 0, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": { "text-generation": { "do_sample": true, "max_length": 50, "temperature": 0.9 } }, "tokenizer_class": "GPT2Tokenizer", "torch_dtype": "float32", "transformers_version": "4.45.2", "use_cache": false, "vocab_size": 50257, "window_size": 256 }