Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -3,12 +3,12 @@ license: cc-by-nc-nd-4.0
|
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
base_model: rizla/rizla-17
|
7 |
model-index:
|
8 |
- name: trrapi-16
|
9 |
results: []
|
10 |
-
datasets:
|
11 |
-
- noxneural/lilium_albanicum_eng_alb
|
12 |
---
|
13 |
|
14 |
|
@@ -28,3 +28,17 @@ git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make -j
|
|
28 |
|
29 |
./server -m ../trrapi-q5km.gguf --port 8080 -c 2000 -cb -t 8 -ngl 80
|
30 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- noxneural/lilium_albanicum_eng_alb
|
8 |
base_model: rizla/rizla-17
|
9 |
model-index:
|
10 |
- name: trrapi-16
|
11 |
results: []
|
|
|
|
|
12 |
---
|
13 |
|
14 |
|
|
|
28 |
|
29 |
./server -m ../trrapi-q5km.gguf --port 8080 -c 2000 -cb -t 8 -ngl 80
|
30 |
```
|
31 |
+
|
32 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
33 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_rizla__trrapi-16b)
|
34 |
+
|
35 |
+
| Metric |Value|
|
36 |
+
|---------------------------------|----:|
|
37 |
+
|Avg. |74.48|
|
38 |
+
|AI2 Reasoning Challenge (25-Shot)|72.10|
|
39 |
+
|HellaSwag (10-Shot) |88.88|
|
40 |
+
|MMLU (5-Shot) |64.26|
|
41 |
+
|TruthfulQA (0-shot) |74.13|
|
42 |
+
|Winogrande (5-shot) |86.35|
|
43 |
+
|GSM8k (5-shot) |61.18|
|
44 |
+
|