| { | |
| "_name_or_path": "./Qwen2.5-72B-Instruct-AutoRound-GPTQ-2bit", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 8192, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 29568, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 70, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 80, | |
| "num_key_value_heads": 8, | |
| "quantization_config": { | |
| "batch_size": 1, | |
| "bits": 2, | |
| "block_name_to_quantize": null, | |
| "cache_block_outputs": true, | |
| "damp_percent": 0.01, | |
| "dataset": null, | |
| "desc_act": false, | |
| "exllama_config": { | |
| "version": 1 | |
| }, | |
| "group_size": 128, | |
| "max_input_length": null, | |
| "model_seqlen": null, | |
| "module_name_preceding_first_block": null, | |
| "modules_in_block_to_quantize": null, | |
| "pad_token_id": null, | |
| "quant_method": "gptq", | |
| "sym": true, | |
| "tokenizer": null, | |
| "true_sequential": false, | |
| "use_cuda_fp16": false, | |
| "use_exllama": true | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.46.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |