初始化项目,由ModelHub XC社区提供模型
Model: codefuse-ai/SWE-CARE-RM Source: Original Platform
This commit is contained in:
11
reward_config.json
Normal file
11
reward_config.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"format_version": 1,
|
||||
"base_model_dir": "Qwen3-8B",
|
||||
"lora_dir": "step_2200",
|
||||
"projector_path": "projector.pth",
|
||||
"proj_arch": "mlp2x_relu",
|
||||
"torch_dtype": "bfloat16",
|
||||
"attn_implementation": null,
|
||||
"trust_remote_code": true,
|
||||
"reward_activation": "sigmoid"
|
||||
}
|
||||
Reference in New Issue
Block a user