xwjiang2010/draft_model
013
1{2 "_name_or_path": "JackFram/llama-160m",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": 768,11 "initializer_range": 0.02,12 "intermediate_size": 3072,13 "max_position_embeddings": 2048,14 "model_type": "llama",15 "num_attention_heads": 12,16 "num_hidden_layers": 12,17 "num_key_value_heads": 12,18 "pretraining_tp": 1,19 "rms_norm_eps": 1e-06,20 "rope_scaling": null,21 "rope_theta": 10000.0,22 "tie_word_embeddings": false,23 "torch_dtype": "float32",24 "transformers_version": "4.35.0.dev0",25 "use_cache": true,26 "vocab_size": 3200027}28 