| { | |
| "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base", | |
| "architectures": [ | |
| "LlamaModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 32013, | |
| "eos_token_id": 32014, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5504, | |
| "max_position_embeddings": 16384, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "modules_to_not_convert": null, | |
| "quant_method": "torchao", | |
| "quant_type": "int8_weight_only", | |
| "quant_type_kwargs": {} | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "factor": 4.0, | |
| "rope_type": "linear", | |
| "type": "linear" | |
| }, | |
| "rope_theta": 100000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32256 | |
| } | |