| { | |
| "_name_or_path": "/mnt/data_large/ccy/my_llama2_7b_gsm8k_mft_10/checkpoint-1170", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "drop_attention_mask": false, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "mask_input": true, | |
| "mask_rate": 0.4, | |
| "max_position_embeddings": 4096, | |
| "mixup": false, | |
| "model_type": "llama", | |
| "neft_all_token": false, | |
| "neftune_alpha": 0, | |
| "not_mask_source": true, | |
| "not_mask_tgt": false, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "only_drop_target": false, | |
| "pretraining_tp": 1, | |
| "replace": true, | |
| "replace_rate": 1.0, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "token_dropout": 0, | |
| "token_noise": false, | |
| "token_noise_hard": false, | |
| "token_noise_random": false, | |
| "token_noise_sample": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.36.2", | |
| "use_cache": true, | |
| "vocab_size": 32002 | |
| } | |