Update README.md
Browse files
README.md
CHANGED
@@ -266,7 +266,25 @@ The corpus is composed as follows:
|
|
266 |
The training was conducted on the MareNostrum V in the Barcelona Supercomputing Center ([BSC](https://www.bsc.es/ca/marenostrum/marenostrum-5)), using 10 nodes with 4 GPUs NVIDIA H100 64GB each one.
|
267 |
|
268 |
## Evaluation
|
269 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
270 |
|
271 |
## Additional information
|
272 |
|
@@ -286,22 +304,3 @@ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLI
|
|
286 |
|
287 |
### Funding
|
288 |
This model was development within the Nós Project, funded by the Ministerio para la Transformación Digital y de la Función Pública - Funded by EU – NextGenerationEU within the framework of the [project ILENIA](https://proyectoilenia.es/) with reference 2022/TL22/00215336.
|
289 |
-
|
290 |
-
|
291 |
-
# Open Portuguese LLM Leaderboard Evaluation Results
|
292 |
-
|
293 |
-
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/Nos-PT/Llama-Carvalho-PT-GL) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
|
294 |
-
|
295 |
-
| Metric | Value |
|
296 |
-
|--------------------------|---------|
|
297 |
-
|Average |**53.39**|
|
298 |
-
|ENEM Challenge (No Images)| 19.38|
|
299 |
-
|BLUEX (No Images) | 18.92|
|
300 |
-
|OAB Exams | 0|
|
301 |
-
|Assin2 RTE | 89.30|
|
302 |
-
|Assin2 STS | 78.18|
|
303 |
-
|FaQuAD NLI | 65.88|
|
304 |
-
|HateBR Binary | 82.83|
|
305 |
-
|PT Hate Speech Binary | 64.84|
|
306 |
-
|tweetSentBR | 61.15|
|
307 |
-
|
|
|
266 |
The training was conducted on the MareNostrum V in the Barcelona Supercomputing Center ([BSC](https://www.bsc.es/ca/marenostrum/marenostrum-5)), using 10 nodes with 4 GPUs NVIDIA H100 64GB each one.
|
267 |
|
268 |
## Evaluation
|
269 |
+
|
270 |
+
### Galician and European Portuguese
|
271 |
+
Soon...
|
272 |
+
### American Portuguese: Open Portuguese LLM Leaderboard Evaluation Results
|
273 |
+
|
274 |
+
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/Nos-PT/Llama-Carvalho-PT-GL) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
|
275 |
+
|
276 |
+
| Metric | Value |
|
277 |
+
|--------------------------|---------|
|
278 |
+
|Average |**53.39**|
|
279 |
+
|ENEM Challenge (No Images)| 19.38|
|
280 |
+
|BLUEX (No Images) | 18.92|
|
281 |
+
|OAB Exams | 0|
|
282 |
+
|Assin2 RTE | 89.30|
|
283 |
+
|Assin2 STS | 78.18|
|
284 |
+
|FaQuAD NLI | 65.88|
|
285 |
+
|HateBR Binary | 82.83|
|
286 |
+
|PT Hate Speech Binary | 64.84|
|
287 |
+
|tweetSentBR | 61.15|
|
288 |
|
289 |
## Additional information
|
290 |
|
|
|
304 |
|
305 |
### Funding
|
306 |
This model was development within the Nós Project, funded by the Ministerio para la Transformación Digital y de la Función Pública - Funded by EU – NextGenerationEU within the framework of the [project ILENIA](https://proyectoilenia.es/) with reference 2022/TL22/00215336.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|