| { | |
| "head_dim": 128, | |
| "hidden_size": 2560, | |
| "intermediate_size": 9728, | |
| "max_position_embeddings": 262144, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 5000000, | |
| "tie_word_embeddings": true, | |
| "vocab_size": 151936 | |
| } |