| { |
| "architectures": [ |
| "Qwen2Model" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "eos_token_id": 151645, |
| "hidden_act": "silu", |
| "hidden_size": 3584, |
| "initializer_range": 0.02, |
| "intermediate_size": 18944, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 28, |
| "model_type": "qwen2", |
| "num_attention_heads": 28, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 4, |
| "quantization_config": { |
| "backend": null, |
| "batch_size": 1, |
| "bits": 4, |
| "block_name_to_quantize": null, |
| "cache_block_outputs": true, |
| "checkpoint_format": "gptq", |
| "damp_percent": 0.1, |
| "dataset": null, |
| "desc_act": true, |
| "exllama_config": { |
| "version": 1 |
| }, |
| "group_size": 128, |
| "max_input_length": null, |
| "meta": { |
| "damp_auto_increment": 0.0025, |
| "damp_percent": 0.01, |
| "mse": 0.0, |
| "quantizer": [ |
| "gptqmodel:2.1.0" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel" |
| }, |
| "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": true, |
| "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": "4.50.1", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 152064 |
| } |
|
|
