Romain-Cosentino
commited on
Commit
•
277cd6f
1
Parent(s):
b7e48ae
readme update
Browse files
README.md
CHANGED
@@ -78,8 +78,6 @@ MT-Bench is a benchmark made up of 80 high-quality multi-turn questions. These q
|
|
78 |
|
79 |
*values reported on [lmsys](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge) ChatBot Arena
|
80 |
|
81 |
-
**The [OpenLLM Leader](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) as of Jan 5, 2024 is the merge model available as [samir-fama/SamirGPT-v1](https://huggingface.co/samir-fama/SamirGPT-v1)
|
82 |
-
|
83 |
![hexplot.png](assets/hexplot.png)
|
84 |
|
85 |
# Limitations
|
|
|
78 |
|
79 |
*values reported on [lmsys](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge) ChatBot Arena
|
80 |
|
|
|
|
|
81 |
![hexplot.png](assets/hexplot.png)
|
82 |
|
83 |
# Limitations
|