ajibawa-2023/Python-Code-13B

1{2  "_name_or_path": "/media/mla100scus/Projects_1/Pycode-13B",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "bos_token_id": 1,7  "eos_token_id": 2,8  "hidden_act": "silu",9  "hidden_size": 5120,10  "initializer_range": 0.02,11  "intermediate_size": 13824,12  "max_position_embeddings": 4096,13  "model_type": "llama",14  "num_attention_heads": 40,15  "num_hidden_layers": 40,16  "num_key_value_heads": 40,17  "pad_token_id": 0,18  "pretraining_tp": 1,19  "rms_norm_eps": 1e-05,20  "rope_scaling": null,21  "tie_word_embeddings": false,22  "torch_dtype": "bfloat16",23  "transformers_version": "4.28.1",24  "use_cache": true,25  "vocab_size": 3200026}27