TaylorAI/Flash-Llama-7B

1{2  "_name_or_path": "togethercomputer/LLaMA-2-7B-32K",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "auto_map": {7    "AutoModelForCausalLM": "modeling_flash_llama.LlamaForCausalLM"8  },9  "bos_token_id": 1,10  "eos_token_id": 2,11  "hidden_act": "silu",12  "hidden_size": 4096,13  "initializer_range": 0.02,14  "intermediate_size": 11008,15  "max_position_embeddings": 32768,16  "model_type": "llama",17  "num_attention_heads": 32,18  "num_hidden_layers": 32,19  "num_key_value_heads": 32,20  "pad_token_id": 0,21  "pretraining_tp": 1,22  "rms_norm_eps": 1e-05,23  "rope_scaling": null,24  "tie_word_embeddings": false,25  "torch_dtype": "float16",26  "transformers_version": "4.31.0",27  "use_cache": true,28  "vocab_size": 3200029}30