| { |
| "architectures": ["Qwen2ForCausalLM"], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "eos_token_id": 151645, |
| "hidden_act": "silu", |
| "hidden_size": 8192, |
| "initializer_range": 0.02, |
| "intermediate_size": 29568, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 70, |
| "model_type": "qwen2", |
| "num_attention_heads": 64, |
| "num_hidden_layers": 80, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 1000000.0, |
| "rope_scaling": { |
| "type": "yarn", |
| "factor": 4.0, |
| "original_max_position_embeddings": 32768 |
| }, |
| "sliding_window": 131072, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.43.1", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 152064 |
| } |