Files
qwen3-4b-latte-v5/adapter_config.json
ModelHub XC 6ed4004b41 初始化项目,由ModelHub XC社区提供模型
Model: latte-agent/qwen3-4b-latte-v5
Source: Original Platform
2026-06-05 18:42:18 +08:00

41 lines
1012 B
JSON

{
"adapter_path": "/Users/muffin/.hermes/distill_adapters_v5",
"batch_size": 1,
"clear_cache_threshold": 0,
"config": null,
"data": "/Users/muffin/.hermes/distill_dataset_v5",
"fine_tune_type": "lora",
"grad_accumulation_steps": 8,
"grad_checkpoint": true,
"iters": 800,
"learning_rate": 0.0001,
"lora_parameters": {
"rank": 8,
"dropout": 0.0,
"scale": 20.0
},
"lr_schedule": null,
"mask_prompt": true,
"max_seq_length": 1536,
"model": "mlx-community/Qwen3-4B-Instruct-2507-4bit",
"num_layers": 8,
"optimizer": "adam",
"optimizer_config": {
"adam": {},
"adamw": {},
"muon": {},
"sgd": {},
"adafactor": {}
},
"project_name": null,
"report_to": null,
"resume_adapter_file": null,
"save_every": 50,
"seed": 42,
"steps_per_eval": 50,
"steps_per_report": 10,
"test": false,
"test_batches": 500,
"train": true,
"val_batches": 25
}