| { | |
| "_name_or_path": "/mnt/shgeminicephfs/wx-dc-plt-hpc/xinshuohu/Output/Embedding/Qwen2-0.5B-eos_mean_pretrain_0806_1e-4_uen_sft_1022_filtered_v2_inst_3node_g8_1e-5_sin-0.1_mrl", | |
| "architectures": [ | |
| "Qwen2Model" | |
| ], | |
| "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, | |
| "max_position_embeddings": 131072, | |
| "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_theta": 1000000.0, | |
| "sliding_window": 131072, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.39.2", | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |