tmmdev/codellama-pattern-analysis
415
1{2 "_name_or_path": "codellama/CodeLlama-7b-hf",3 "architectures": [4 "LlamaForCausalLM"5 ],6 "bos_token_id": 1,7 "eos_token_id": 2,8 "hidden_act": "silu",9 "hidden_size": 4096,10 "initializer_range": 0.02,11 "intermediate_size": 11008,12 "max_position_embeddings": 16384,13 "model_type": "llama",14 "num_attention_heads": 32,15 "num_hidden_layers": 32,16 "num_key_value_heads": 32,17 "pretraining_tp": 1,18 "rms_norm_eps": 1e-05,19 "rope_scaling": null,20 "rope_theta": 1000000,21 "tie_word_embeddings": false,22 "torch_dtype": "bfloat16",23 "transformers_version": "4.33.0.dev0",24 "use_cache": true,25 "vocab_size": 3201626}27 