LLM-Blender

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.

yuchenlin/LLM-Blender

View on GitHub ↗

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.

LLM-Blender grew +0.2% in the last 30 days, ranks 43rd of 346 in Training Toolkits, last commit 730 days ago.

Star trajectory

77 days tracked
2026-08-07997 stars today2026-10-23
Momentum

+0.2% in 30d, above the Training Toolkits median of +0.0%.

Maintenance

Last commit 730 days ago, staler than the median of 225d.

How it compares in Training Toolkits

LLM-Blender
997
stars
+0.2% 30d
commit 730 days ago
Training Toolkits median
326.5
stars
+0.0% 30d
commit ~225d ago
Leader · TTS
46.1k
stars
+0.2% 30d
commit 797 days ago

Ranked 43rd of 346 by stars.

Language
Python
License
Apache License 2.0
Contributors
2
Forks
91
Watchers
19
Open issues
3
Releases
0
Created
2023-05-31
Stars this week
+0

You've seen where LLM-Blender stands today.

Get the moves before everyone else: the 5 Training Toolkits repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain LLM-Blender?

Claim this page to add your own call-to-action.

Claim this page