| { |
| "_name_or_path": "Qwen/Qwen2.5-14B-Instruct", |
| "architectures": [ |
| "Qwen2ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "eos_token_id": 151645, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 13824, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 70, |
| "model_type": "qwen2", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 48, |
| "num_key_value_heads": 8, |
| "quantization_config": { |
| "amp": true, |
| "autoround_version": "0.4.5", |
| "batch_size": 8, |
| "bits": 2, |
| "damp_percent": 0.01, |
| "data_type": "int", |
| "desc_act": false, |
| "enable_minmax_tuning": true, |
| "enable_norm_bias_tuning": false, |
| "enable_quanted_input": true, |
| "gradient_accumulate_steps": 1, |
| "group_size": 32, |
| "iters": 500, |
| "low_gpu_mem_usage": false, |
| "lr": 0.002, |
| "minmax_lr": 0.002, |
| "nsamples": 512, |
| "quant_method": "gptq", |
| "scale_dtype": "torch.float16", |
| "seqlen": 2048, |
| "sym": true, |
| "to_quant_block_names": null, |
| "true_sequential": false |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "sliding_window": 131072, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.49.0", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 152064 |
| } |
|
|
