| { | |
| "_name_or_path": "/egr/research-optml/chongyu/NEW-BLUE/TOFU/paper_models/final_ft_noLORA_5_epochs_inst_lr1e-05_llama2-7b_full_seed42_1/checkpoint-625/unlearned/8GPU_simnpo_grad_diff_1e-05_forget10_epoch10_batch1_accum4_beta4.5_gamma0.0_grad_diff_coeff0.125_reffine_tuned_evalsteps_per_epoch_seed1001_1/checkpoint-125", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.0.dev0", | |
| "use_cache": false, | |
| "vocab_size": 32000 | |
| } | |