ramixpe/1.8testing

1{2  "_name_or_path": "/home/rami/.cache/modelscope/hub/qwen/Qwen-1_8B",3  "architectures": [4    "QWenLMHeadModel"5  ],6  "attn_dropout_prob": 0.0,7  "auto_map": {8    "AutoConfig": "configuration_qwen.QWenConfig",9    "AutoModel": "modeling_qwen.QWenLMHeadModel",10    "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"11  },12  "bf16": false,13  "emb_dropout_prob": 0.0,14  "fp16": true,15  "fp32": false,16  "hidden_size": 2048,17  "initializer_range": 0.02,18  "intermediate_size": 11008,19  "kv_channels": 128,20  "layer_norm_epsilon": 1e-06,21  "max_position_embeddings": 8192,22  "model_type": "qwen",23  "no_bias": true,24  "num_attention_heads": 16,25  "num_hidden_layers": 24,26  "onnx_safe": null,27  "rotary_emb_base": 10000,28  "rotary_pct": 1.0,29  "scale_attn_weights": true,30  "seq_length": 8192,31  "softmax_in_fp32": false,32  "tie_word_embeddings": false,33  "tokenizer_class": "QWenTokenizer",34  "torch_dtype": "float16",35  "transformers_version": "4.37.2",36  "use_cache": true,37  "use_cache_kernel": false,38  "use_cache_quantization": false,39  "use_dynamic_ntk": true,40  "use_flash_attn": true,41  "use_logn_attn": true,42  "vocab_size": 15193643}44