FasterDecoding/medusa-v1.0-vicuna-7b-v1.5

1{2  "_name_or_path": "lmsys/vicuna-7b-v1.5",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "bos_token_id": 1,8  "eos_token_id": 2,9  "hidden_act": "silu",10  "hidden_size": 4096,11  "initializer_range": 0.02,12  "intermediate_size": 11008,13  "max_position_embeddings": 4096,14  "model_type": "llama",15  "num_attention_heads": 32,16  "num_hidden_layers": 32,17  "num_key_value_heads": 32,18  "pad_token_id": 0,19  "pretraining_tp": 1,20  "rms_norm_eps": 1e-05,21  "rope_scaling": null,22  "rope_theta": 10000.0,23  "tie_word_embeddings": false,24  "torch_dtype": "float16",25  "transformers_version": "4.34.0",26  "use_cache": false,27  "vocab_size": 32000,28  "medusa_num_heads": 5,29  "medusa_num_layers": 130}31