Upload from /robust_llm_data/checkpoints/oskar_041l_ft_pythia_jailbreaks_float32/oskar-041l-ft-pythia-jailbreaks-float32-0000/af2d85435eb4a3723a41ce05b6a7fb0a6be6de1c463c8f2f10776f8a06b4ef0e/epoch_0003/model by /root/robust-llm/scripts/oskar/push_checkpoints_to_hub.py
20c6307
verified
| { | |
| "_name_or_path": "EleutherAI/pythia-14m", | |
| "architectures": [ | |
| "GPTNeoXForCausalLM" | |
| ], | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "classifier_dropout": 0.1, | |
| "eos_token_id": 0, | |
| "hidden_act": "gelu", | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 128, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 512, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "gpt_neox", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 6, | |
| "pad_token_id": 0, | |
| "partial_rotary_factor": 0.25, | |
| "problem_type": "single_label_classification", | |
| "rope_scaling": null, | |
| "rope_theta": 10000, | |
| "rotary_emb_base": 10000, | |
| "rotary_pct": 0.25, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.2", | |
| "use_cache": false, | |
| "use_parallel_residual": true, | |
| "vocab_size": 50304 | |
| } | |