| { | |
| "_name_or_path": "/mnt/bn/trung-nas/ppo_paper_final_new/_models_outputs_sft/gsm8k_python_sdp_codellama/global_step_2926_epoch_19/", | |
| "architectures": [ | |
| "LlamaForSequenceClassification" | |
| ], | |
| "attention_bias": false, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 16384, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 1, | |
| "pretraining_tp": 1, | |
| "problem_type": "single_label_classification", | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.34.1", | |
| "use_cache": true, | |
| "vocab_size": 32016 | |
| } | |