初始化项目,由ModelHub XC社区提供模型
Model: espressovi/BODHI-qwen-3-8b-distil Source: Original Platform
This commit is contained in:
20
README.md
Normal file
20
README.md
Normal file
@@ -0,0 +1,20 @@
|
||||
---
|
||||
license: mit
|
||||
datasets:
|
||||
- espressovi/BODHI-distillation
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- Qwen/Qwen3-8B-Base
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# BODHI
|
||||
|
||||
Artifact for BODHI project. This **math** model is created by Long-CoT distillation starting from ```Qwen/Qwen3-8B-Base```.
|
||||
|
||||
## Performance
|
||||
|
||||
The following results are at T=1.0, 16K tokens and pass@8.
|
||||
|
||||
**AIME25**: 18.82 %
|
||||
Reference in New Issue
Block a user