{ "_name_or_path": "D:\\\\gptq\\\\internlm-chat-7b-v1_1", "architectures": [ "InternLMForCausalLM" ], "auto_map": { "AutoConfig": "configuration_internlm.InternLMConfig", "AutoModel": "modeling_internlm.InternLMForCausalLM", "AutoModelForCausalLM": "modeling_internlm.InternLMForCausalLM" }, "bias": true, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 2048, "model_type": "internlm", "num_attention_heads": 32, "num_hidden_layers": 32, "pad_token_id": 2, "quantization_config": { "batch_size": 1, "bits": 4, "block_name_to_quantize": "model.layers", "cache_block_outputs": true, "damp_percent": 0.1, "dataset": "c4", "desc_act": false, "exllama_config": { "version": 1 }, "group_size": 128, "max_input_length": null, "model_seqlen": 2048, "module_name_preceding_first_block": [ "model.embed_tokens" ], "pad_token_id": null, "quant_method": "gptq", "sym": true, "tokenizer": null, "true_sequential": true, "use_cuda_fp16": true, "use_exllama": true }, "rms_norm_eps": 1e-06, "rotary": { "base": 10000, "type": "dynamic" }, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.36.0.dev0", "use_cache": true, "vocab_size": 103168 }