| { | |
| "architecture": "custom_transformer", | |
| "hidden_size": 4096, | |
| "intermediate_size": 11008, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "vocab_size": 32000, | |
| "max_position_embeddings": 4096, | |
| "quantization_type": "8-bit", | |
| "tensor_type": "int8", | |
| "system_prompt": "" | |
| } |