| { |
| "_name_or_path": "/hpi/fs00/share/fg/meinel/nianhui.guo/deepseek/models--deepseek-ai--DeepSeek-R1-Distill-Qwen-14B/snapshots/6453600843497f04e63f069049e92bf221d9e000/", |
| "architectures": [ |
| "Qwen2ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "eos_token_id": 151643, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 13824, |
| "max_position_embeddings": 131072, |
| "max_window_layers": 48, |
| "model_type": "qwen2", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 48, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 1000000.0, |
| "sliding_window": 131072, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.40.0", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 152064 |
| } |
|
|