kevinpro/MathOctopus-MAPO-DPO-13B

1{2  "_name_or_path": "/mnt/data/shesj/Trained/RL4CoT/DPO/Parallel_13B_numglueCorrect_extend_10lang_v3_iter1.json/checkpoint-1600",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 1,9  "end_token_id": 2,10  "eos_token_id": 2,11  "hidden_act": "silu",12  "hidden_size": 5120,13  "initializer_range": 0.02,14  "intermediate_size": 13824,15  "max_position_embeddings": 2048,16  "model_type": "llama",17  "num_attention_heads": 40,18  "num_hidden_layers": 40,19  "num_key_value_heads": 40,20  "pad_token_id": 2,21  "pretraining_tp": 1,22  "rms_norm_eps": 1e-05,23  "rope_scaling": null,24  "rope_theta": 10000.0,25  "tie_word_embeddings": false,26  "torch_dtype": "bfloat16",27  "transformers_version": "4.36.2",28  "use_cache": false,29  "vocab_size": 3200030}31