rd211/Qwen2.5-14B-Instruct-MathDial

1{2  "_name_or_path": "Qwen/Qwen2.5-14B-Instruct",3  "architectures": [4    "Qwen2ForCausalLM"5  ],6  "attention_dropout": 0.0,7  "bos_token_id": 151643,8  "eos_token_id": 151645,9  "hidden_act": "silu",10  "hidden_size": 5120,11  "initializer_range": 0.02,12  "intermediate_size": 13824,13  "max_position_embeddings": 32768,14  "max_window_layers": 70,15  "model_type": "qwen2",16  "num_attention_heads": 40,17  "num_hidden_layers": 48,18  "num_key_value_heads": 8,19  "rms_norm_eps": 1e-06,20  "rope_scaling": null,21  "rope_theta": 1000000.0,22  "sliding_window": 131072,23  "tie_word_embeddings": false,24  "torch_dtype": "bfloat16",25  "transformers_version": "4.49.0",26  "use_cache": true,27  "use_sliding_window": false,28  "vocab_size": 15206429}30