Mathoctopus/Parallel_xRFT_13B

1{2  "_name_or_path": "/cpfs/shared/nlp/llama2/llama-2-13b-hf",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "bos_token_id": 1,7  "end_token_id": 2,8  "eos_token_id": 2,9  "hidden_act": "silu",10  "hidden_size": 5120,11  "initializer_range": 0.02,12  "intermediate_size": 13824,13  "max_position_embeddings": 2048,14  "model_type": "llama",15  "num_attention_heads": 40,16  "num_hidden_layers": 40,17  "num_key_value_heads": 40,18  "pad_token_id": 2,19  "rms_norm_eps": 1e-05,20  "tie_word_embeddings": false,21  "torch_dtype": "float16",22  "transformers_version": "4.29.2",23  "use_cache": true,24  "vocab_size": 3200025}26