Hugging Face's logo

m42-health
/
Llama3-Med42-70B

Text Generation
Transformers
Safetensors
English
llama
m42
health
healthcare
clinical-llm
conversational
text-generation-inference
Model card Files Community
5
cchristophe commited on
Commit
fa27e05
•
1 Parent(s): 125cc61

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -22,12 +22,12 @@ Med42-v2 is a suite of open-access clinical large language models (LLM) instruct
22
 
23
  |Models|Elo Score|
24
  |:---:|:---:|
25
- |Med42-v2-70B| 1764 |
26
  |Llama3-70B-Instruct| 1643 |
27
  |GPT4-o| 1426 |
28
  |Llama3-8B-Instruct| 1352 |
29
  |Mixtral-8x7b-Instruct| 970 |
30
- |Med42-v2-8B| 924 |
31
  |OpenBioLLM-70B| 657 |
32
  |JSL-MedLlama-3-8B-v2.0| 447 |
33
 
@@ -150,12 +150,12 @@ Which response is of higher overall quality in a medical context? Consider:
150
  #### Elo Ratings
151
  |Models|Elo Score|
152
  |:---:|:---:|
153
- |Med42-v2-70B| 1764 |
154
  |Llama3-70B-Instruct| 1643 |
155
  |GPT4-o| 1426 |
156
  |Llama3-8B-Instruct| 1352 |
157
  |Mixtral-8x7b-Instruct| 970 |
158
- |Med42-v2-8B| 924 |
159
  |OpenBioLLM-70B| 657 |
160
  |JSL-MedLlama-3-8B-v2.0| 447 |
161
 
@@ -170,8 +170,8 @@ Med42-v2 improves performance on every clinical benchmark compared to our previo
170
 
171
  |Model|MMLU Pro|MMLU|MedMCQA|MedQA|USMLE|
172
  |---:|:---:|:---:|:---:|:---:|:---:|
173
- |Med42v2-70B|64.36|87.12|73.20|79.10|83.80|
174
- |Med42v2-8B|54.30|75.76|61.34|62.84|67.04|
175
  |OpenBioLLM|64.24|90.40|73.18|76.90|79.01|
176
  |GPT-4.0<sup>&dagger;</sup>|-|87.00|69.50|78.90|84.05|
177
  |MedGemini*|-|-|-|84.00|-|
 
22
 
23
  |Models|Elo Score|
24
  |:---:|:---:|
25
+ |**Med42-v2-70B**| 1764 |
26
  |Llama3-70B-Instruct| 1643 |
27
  |GPT4-o| 1426 |
28
  |Llama3-8B-Instruct| 1352 |
29
  |Mixtral-8x7b-Instruct| 970 |
30
+ |**Med42-v2-8B**| 924 |
31
  |OpenBioLLM-70B| 657 |
32
  |JSL-MedLlama-3-8B-v2.0| 447 |
33
 
 
150
  #### Elo Ratings
151
  |Models|Elo Score|
152
  |:---:|:---:|
153
+ |**Med42-v2-70B**| 1764 |
154
  |Llama3-70B-Instruct| 1643 |
155
  |GPT4-o| 1426 |
156
  |Llama3-8B-Instruct| 1352 |
157
  |Mixtral-8x7b-Instruct| 970 |
158
+ |**Med42-v2-8B**| 924 |
159
  |OpenBioLLM-70B| 657 |
160
  |JSL-MedLlama-3-8B-v2.0| 447 |
161
 
 
170
 
171
  |Model|MMLU Pro|MMLU|MedMCQA|MedQA|USMLE|
172
  |---:|:---:|:---:|:---:|:---:|:---:|
173
+ |**Med42v2-70B**|64.36|87.12|73.20|79.10|83.80|
174
+ |**Med42v2-8B**|54.30|75.76|61.34|62.84|67.04|
175
  |OpenBioLLM|64.24|90.40|73.18|76.90|79.01|
176
  |GPT-4.0<sup>&dagger;</sup>|-|87.00|69.50|78.90|84.05|
177
  |MedGemini*|-|-|-|84.00|-|