Adding the Open Portuguese LLM Leaderboard Evaluation Results
#1
by
leaderboard-pt-pr-bot
- opened
README.md
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: mit
|
3 |
-
library_name:
|
4 |
tags:
|
5 |
- DPO
|
6 |
- WeniGPT
|
@@ -8,7 +10,6 @@ base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-LLM_Base_2.0.3_SFT
|
|
8 |
model-index:
|
9 |
- name: Weni/WeniGPT-2.4.1-Zephyr-7B-3-epochs-LLM_Base_2.0.3_DPO
|
10 |
results: []
|
11 |
-
language: ['pt']
|
12 |
---
|
13 |
|
14 |
# Weni/WeniGPT-2.4.1-Zephyr-7B-3-epochs-LLM_Base_2.0.3_DPO
|
@@ -84,3 +85,22 @@ The following hyperparameters were used during training:
|
|
84 |
|
85 |
### Hardware
|
86 |
- Cloud provided: runpod.io
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- pt
|
4 |
license: mit
|
5 |
+
library_name: trl
|
6 |
tags:
|
7 |
- DPO
|
8 |
- WeniGPT
|
|
|
10 |
model-index:
|
11 |
- name: Weni/WeniGPT-2.4.1-Zephyr-7B-3-epochs-LLM_Base_2.0.3_DPO
|
12 |
results: []
|
|
|
13 |
---
|
14 |
|
15 |
# Weni/WeniGPT-2.4.1-Zephyr-7B-3-epochs-LLM_Base_2.0.3_DPO
|
|
|
85 |
|
86 |
### Hardware
|
87 |
- Cloud provided: runpod.io
|
88 |
+
|
89 |
+
|
90 |
+
# Open Portuguese LLM Leaderboard Evaluation Results
|
91 |
+
|
92 |
+
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/Weni/WeniGPT-2.4.1-Zephyr-7B-3-epochs-GPT-QA-1.0.1_DP_DPO) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
|
93 |
+
|
94 |
+
| Metric | Value |
|
95 |
+
|--------------------------|---------|
|
96 |
+
|Average |**61.64**|
|
97 |
+
|ENEM Challenge (No Images)| 56.26|
|
98 |
+
|BLUEX (No Images) | 47.43|
|
99 |
+
|OAB Exams | 38.22|
|
100 |
+
|Assin2 RTE | 88.45|
|
101 |
+
|Assin2 STS | 68.73|
|
102 |
+
|FaQuAD NLI | 61.31|
|
103 |
+
|HateBR Binary | 80.71|
|
104 |
+
|PT Hate Speech Binary | 66.08|
|
105 |
+
|tweetSentBR | 47.53|
|
106 |
+
|