leaderboard-pr-bot
commited on
Commit
•
de122fb
1
Parent(s):
339ae47
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
@@ -1,16 +1,19 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
inference: false
|
3 |
base_model:
|
4 |
- SanjiWatsuki/Silicon-Maid-7B
|
5 |
- sethuiyer/Aika-7B
|
6 |
- sethuiyer/Nandine-7b
|
7 |
- mlabonne/AlphaMonarch-7B
|
8 |
-
|
9 |
-
tags:
|
10 |
-
- mergekit
|
11 |
-
- merge
|
12 |
-
- not-for-all-audiences
|
13 |
-
license: cc
|
14 |
model-index:
|
15 |
- name: sethuiyer/Diana-7B
|
16 |
results:
|
@@ -29,8 +32,7 @@ model-index:
|
|
29 |
value: 68.34
|
30 |
name: normalized accuracy
|
31 |
source:
|
32 |
-
url:
|
33 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
34 |
name: Open LLM Leaderboard
|
35 |
- task:
|
36 |
type: text-generation
|
@@ -46,8 +48,7 @@ model-index:
|
|
46 |
value: 86.73
|
47 |
name: normalized accuracy
|
48 |
source:
|
49 |
-
url:
|
50 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
51 |
name: Open LLM Leaderboard
|
52 |
- task:
|
53 |
type: text-generation
|
@@ -64,8 +65,7 @@ model-index:
|
|
64 |
value: 64.58
|
65 |
name: accuracy
|
66 |
source:
|
67 |
-
url:
|
68 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
69 |
name: Open LLM Leaderboard
|
70 |
- task:
|
71 |
type: text-generation
|
@@ -81,8 +81,7 @@ model-index:
|
|
81 |
- type: mc2
|
82 |
value: 60.55
|
83 |
source:
|
84 |
-
url:
|
85 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
86 |
name: Open LLM Leaderboard
|
87 |
- task:
|
88 |
type: text-generation
|
@@ -99,8 +98,7 @@ model-index:
|
|
99 |
value: 80.19
|
100 |
name: accuracy
|
101 |
source:
|
102 |
-
url:
|
103 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
104 |
name: Open LLM Leaderboard
|
105 |
- task:
|
106 |
type: text-generation
|
@@ -117,12 +115,8 @@ model-index:
|
|
117 |
value: 63.23
|
118 |
name: accuracy
|
119 |
source:
|
120 |
-
url:
|
121 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
122 |
name: Open LLM Leaderboard
|
123 |
-
language:
|
124 |
-
- en
|
125 |
-
pipeline_tag: text-generation
|
126 |
---
|
127 |
# Diana-7B
|
128 |
|
@@ -198,3 +192,17 @@ GGUF files are available at [Diana-7B-GGUF](https://huggingface.co/sethuiyer/Dia
|
|
198 |
Diana is now available on Ollama. You can use it by running the command ```ollama run stuehieyr/diana``` in your
|
199 |
terminal. If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on
|
200 |
a Google Colab backend.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: cc
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- merge
|
9 |
+
- not-for-all-audiences
|
10 |
inference: false
|
11 |
base_model:
|
12 |
- SanjiWatsuki/Silicon-Maid-7B
|
13 |
- sethuiyer/Aika-7B
|
14 |
- sethuiyer/Nandine-7b
|
15 |
- mlabonne/AlphaMonarch-7B
|
16 |
+
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
17 |
model-index:
|
18 |
- name: sethuiyer/Diana-7B
|
19 |
results:
|
|
|
32 |
value: 68.34
|
33 |
name: normalized accuracy
|
34 |
source:
|
35 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
|
|
36 |
name: Open LLM Leaderboard
|
37 |
- task:
|
38 |
type: text-generation
|
|
|
48 |
value: 86.73
|
49 |
name: normalized accuracy
|
50 |
source:
|
51 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
|
|
52 |
name: Open LLM Leaderboard
|
53 |
- task:
|
54 |
type: text-generation
|
|
|
65 |
value: 64.58
|
66 |
name: accuracy
|
67 |
source:
|
68 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
|
|
69 |
name: Open LLM Leaderboard
|
70 |
- task:
|
71 |
type: text-generation
|
|
|
81 |
- type: mc2
|
82 |
value: 60.55
|
83 |
source:
|
84 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
|
|
85 |
name: Open LLM Leaderboard
|
86 |
- task:
|
87 |
type: text-generation
|
|
|
98 |
value: 80.19
|
99 |
name: accuracy
|
100 |
source:
|
101 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
|
|
102 |
name: Open LLM Leaderboard
|
103 |
- task:
|
104 |
type: text-generation
|
|
|
115 |
value: 63.23
|
116 |
name: accuracy
|
117 |
source:
|
118 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
|
|
|
119 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
120 |
---
|
121 |
# Diana-7B
|
122 |
|
|
|
192 |
Diana is now available on Ollama. You can use it by running the command ```ollama run stuehieyr/diana``` in your
|
193 |
terminal. If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on
|
194 |
a Google Colab backend.
|
195 |
+
|
196 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
197 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sethuiyer__Diana-7B)
|
198 |
+
|
199 |
+
| Metric |Value|
|
200 |
+
|---------------------------------|----:|
|
201 |
+
|Avg. |70.60|
|
202 |
+
|AI2 Reasoning Challenge (25-Shot)|68.34|
|
203 |
+
|HellaSwag (10-Shot) |86.73|
|
204 |
+
|MMLU (5-Shot) |64.58|
|
205 |
+
|TruthfulQA (0-shot) |60.55|
|
206 |
+
|Winogrande (5-shot) |80.19|
|
207 |
+
|GSM8k (5-shot) |63.23|
|
208 |
+
|