nvidia/OpenMath-CodeLlama-13b-Python-hf

1{2  "_name_or_path": "nvidia/OpenMath-CodeLlama-13b-Python-hf",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 1,9  "eos_token_id": 2,10  "hidden_act": "silu",11  "hidden_size": 5120,12  "initializer_range": 0.02,13  "intermediate_size": 13824,14  "max_position_embeddings": 16384,15  "model_type": "llama",16  "num_attention_heads": 40,17  "num_hidden_layers": 40,18  "num_key_value_heads": 40,19  "pretraining_tp": 1,20  "rms_norm_eps": 1e-05,21  "rope_scaling": null,22  "rope_theta": 1000000,23  "tie_word_embeddings": false,24  "torch_dtype": "bfloat16",25  "transformers_version": "4.37.2",26  "use_cache": true,27  "vocab_size": 3200028}29