| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "model_type": "llama", | |
| "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.45.0", | |
| "use_cache": true, | |
| "vocab_size": 32000, | |
| "hidden_size": 2048, | |
| "intermediate_size": 5632, | |
| "num_hidden_layers": 24, | |
| "num_attention_heads": 16, | |
| "num_key_value_heads": 16, | |
| "max_position_embeddings": 4096, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "mlp_bias": false | |
| } |