| { | |
| "step": 12500, | |
| "fold": { | |
| "lora": 0, | |
| "lora+qat": 112, | |
| "qat_linear": 147, | |
| "act_fq": 0, | |
| "embedding": 1 | |
| }, | |
| "variants": { | |
| "q4": { | |
| "graphs": { | |
| "audio_encoder": "audio_encoder_q4.onnx", | |
| "tool_encoder": "tool_encoder_q4.onnx", | |
| "decoder_step": "decoder_step_q4.onnx" | |
| }, | |
| "scheme": { | |
| "bits": 4, | |
| "group_size": 32, | |
| "embedding": true, | |
| "audio_encoder": true, | |
| "conv_bits": 8 | |
| }, | |
| "accuracy_level": 4, | |
| "compute": "int4 MatMulNBits / GatherBlockQuantized" | |
| } | |
| }, | |
| "sample_rate": 16000, | |
| "max_audio_seconds": 30.0, | |
| "max_tools_len": 2048, | |
| "max_answer_len": 128, | |
| "tools_json": "Python json.dumps(tools) defaults: ', ' and ': ' separators, ensure_ascii", | |
| "special_tokens": { | |
| "pad": 0, | |
| "eos": 1, | |
| "bos": 2, | |
| "unk": 3, | |
| "tool_call": 4, | |
| "tools": 5 | |
| }, | |
| "vocab_size": 8192, | |
| "d_model": 512, | |
| "num_decoder_layers": 8, | |
| "num_kv_heads": 4, | |
| "head_dim": 64 | |
| } | |