| { |
| "_name_or_path": "/lustre/projects/polyullm/yggu/models/Qwen2.5-0.5B-fix", |
| "architectures": [ |
| "Qwen2ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "eos_token_id": 151643, |
| "hidden_act": "silu", |
| "hidden_size": 896, |
| "initializer_range": 0.02, |
| "intermediate_size": 4864, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 32768, |
| "max_window_layers": 24, |
| "model_type": "qwen2", |
| "num_attention_heads": 14, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 2, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": true, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.46.3", |
| "use_cache": false, |
| "use_mrope": false, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
|
|
