TinyPixel/CodeLlama-7B-Instruct-bf16-sharded

1{2  "_name_or_path": "TheBloke/CodeLlama-7B-Instruct-fp16",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "auto_map": {7    "AutoConfig": "TheBloke/CodeLlama-7B-Instruct-fp16--configuration_llama.LlamaConfig",8    "AutoModel": "TheBloke/CodeLlama-7B-Instruct-fp16--modeling_llama.LlamaModel",9    "AutoModelForCausalLM": "TheBloke/CodeLlama-7B-Instruct-fp16--modeling_llama.LlamaForCausalLM",10    "AutoModelForSequenceClassification": "TheBloke/CodeLlama-7B-Instruct-fp16--modeling_llama.LlamaForSequenceClassification"11  },12  "bos_token_id": 1,13  "eos_token_id": 2,14  "hidden_act": "silu",15  "hidden_size": 4096,16  "initializer_range": 0.02,17  "intermediate_size": 11008,18  "max_position_embeddings": 16384,19  "model_type": "llama",20  "num_attention_heads": 32,21  "num_hidden_layers": 32,22  "num_key_value_heads": 32,23  "pretraining_tp": 1,24  "rms_norm_eps": 1e-05,25  "rope_scaling": null,26  "rope_theta": 1000000,27  "tie_word_embeddings": false,28  "torch_dtype": "bfloat16",29  "transformers_version": "4.30.2",30  "use_cache": true,31  "vocab_size": 3201632}33