Qwen/Qwen2.5-Math-72B-Instruct
31893
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 151643,7 "eos_token_id": 151645,8 "hidden_act": "silu",9 "hidden_size": 8192,10 "initializer_range": 0.02,11 "intermediate_size": 29568,12 "max_position_embeddings": 4096,13 "max_window_layers": 70,14 "model_type": "qwen2",15 "num_attention_heads": 64,16 "num_hidden_layers": 80,17 "num_key_value_heads": 8,18 "rms_norm_eps": 1e-06,19 "rope_theta": 10000.0,20 "sliding_window": 4096,21 "tie_word_embeddings": false,22 "torch_dtype": "bfloat16",23 "transformers_version": "4.43.1",24 "use_cache": true,25 "use_sliding_window": false,26 "vocab_size": 15206427}28 