Upload from /robust_llm_data/checkpoints/oskar_059d_ft_qwen_jailbreaks_instruct_value/oskar-059d-ft-qwen-jailbreaks-instruct-value-0000/1a9b221c7254e4d9d9570759152c37a73230369490f3693bc6ab42765339a9bd/epoch_0003/model by /root/robust-llm/scripts/oskar/push_checkpoints_to_hub.py
f1967ff
verified
| { | |
| "_name_or_path": "Qwen/Qwen2.5-7B-Instruct", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 151643, | |
| "problem_type": "single_label_classification", | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.2", | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |