初始化项目,由ModelHub XC社区提供模型
Model: ForSureTesterSim/QwenR1-7B-Breadcrumbs-TIES Source: Original Platform
This commit is contained in:
11
mergekit_config.yml
Normal file
11
mergekit_config.yml
Normal file
@@ -0,0 +1,11 @@
|
||||
merge_method: breadcrumbs_ties
|
||||
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
|
||||
parameters:
|
||||
density: 0.15 # Retain top 15% (Trims bottom 85% SFT noise)
|
||||
gamma: 0.99 # Trim the top 1% (Destroys extreme RL outliers)
|
||||
weight: 1.0
|
||||
models:
|
||||
- model: nvidia/AceReason-Nemotron-7B
|
||||
- model: ./padded-maestro
|
||||
- model: POLARIS-Project/Polaris-7B-Preview
|
||||
dtype: bfloat16
|
||||
Reference in New Issue
Block a user