Update README.md
Browse files
README.md
CHANGED
@@ -119,10 +119,10 @@ nature and sensitivity of the messages.
|
|
119 |
|
120 |
The finetuned Gemma-2 model was evaluated against the ese models were evaluated against GPT-3.5-Turbo, GPT-4o-mini, and GPT-4o models:
|
121 |
|
122 |
-
| Metric
|
123 |
-
| ------
|
124 |
-
| Accuracy
|
125 |
-
| AUC
|
126 |
|
127 |
## Usage and Limitations
|
128 |
|
@@ -198,10 +198,12 @@ Risks identified and mitigations:
|
|
198 |
|
199 |
[example-maternal-health-rules]: https://saferbirth.org/aim-resources/aim-cornerstones/urgent-maternal-warning-signs-2/
|
200 |
[prohibited-use]: https://ai.google.dev/gemma/prohibited_use_policy
|
201 |
-
|
|
|
202 |
#### Hardware
|
203 |
|
204 |
Inference: NVIDIA L4 GPU
|
|
|
205 |
Training: NVIDIA A100 80 GB
|
206 |
|
207 |
## Citation [optional]
|
|
|
119 |
|
120 |
The finetuned Gemma-2 model was evaluated against the ese models were evaluated against GPT-3.5-Turbo, GPT-4o-mini, and GPT-4o models:
|
121 |
|
122 |
+
| Metric | gemma-2-2b-it-ud | GPT-3.5-Turbo-1106 | GPT-4o-mini-2024-07-18 | GPT-4o-2024-08-06 |
|
123 |
+
| ------ | ---------------- | ------------------ | ---------------------- | ----------------- |
|
124 |
+
| Accuracy | 0.87 | 0.83 | 0.90 | 0.92 |
|
125 |
+
| AUC | 0.84 | 0.83 | 0.91 | 0.92 |
|
126 |
|
127 |
## Usage and Limitations
|
128 |
|
|
|
198 |
|
199 |
[example-maternal-health-rules]: https://saferbirth.org/aim-resources/aim-cornerstones/urgent-maternal-warning-signs-2/
|
200 |
[prohibited-use]: https://ai.google.dev/gemma/prohibited_use_policy
|
201 |
+
[rai-toolkit]: https://ai.google.dev/responsible
|
202 |
+
|
203 |
#### Hardware
|
204 |
|
205 |
Inference: NVIDIA L4 GPU
|
206 |
+
|
207 |
Training: NVIDIA A100 80 GB
|
208 |
|
209 |
## Citation [optional]
|