cchristophe
commited on
Commit
•
89bd376
1
Parent(s):
d0d3192
Update README.md
Browse files
README.md
CHANGED
@@ -21,6 +21,7 @@ Med42-v2 is a suite of open-access clinical large language models (LLM) instruct
|
|
21 |
- Med42-v2-70B sit at the top of the Clinical Elo Rating Leaderboard.
|
22 |
|
23 |
|Models|Elo Score|
|
|
|
24 |
|Med42-v2-70B| --- |
|
25 |
|Llama3-70B-Instruct| --- |
|
26 |
|GPT4-o| --- |
|
@@ -168,6 +169,7 @@ Which response is of higher overall quality in a medical context? Consider:
|
|
168 |
|
169 |
#### Elo Ratings
|
170 |
|Models|Elo Score|
|
|
|
171 |
|Med42-v2-70B| --- |
|
172 |
|Llama3-70B-Instruct| --- |
|
173 |
|GPT4-o| --- |
|
|
|
21 |
- Med42-v2-70B sit at the top of the Clinical Elo Rating Leaderboard.
|
22 |
|
23 |
|Models|Elo Score|
|
24 |
+
|:---:|:---:|
|
25 |
|Med42-v2-70B| --- |
|
26 |
|Llama3-70B-Instruct| --- |
|
27 |
|GPT4-o| --- |
|
|
|
169 |
|
170 |
#### Elo Ratings
|
171 |
|Models|Elo Score|
|
172 |
+
|:---:|:---:|
|
173 |
|Med42-v2-70B| --- |
|
174 |
|Llama3-70B-Instruct| --- |
|
175 |
|GPT4-o| --- |
|