leaderboard-pr-bot
commited on
Commit
•
c3007b6
1
Parent(s):
f4abf43
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
@@ -1,14 +1,109 @@
|
|
1 |
---
|
2 |
-
license: llama3.1
|
3 |
-
library_name: transformers
|
4 |
-
datasets:
|
5 |
-
- Locutusque/hercules-v6.1
|
6 |
language:
|
7 |
- en
|
8 |
- zh
|
9 |
-
|
|
|
10 |
tags:
|
11 |
- not-for-all-audiences
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
---
|
13 |
# Model Card: Locutusque/Hercules-6.1-Llama-3.1-8B
|
14 |
|
@@ -69,3 +164,17 @@ Hercules-6.1-Llama-3.1-8B is well-suited to the following applications:
|
|
69 |
|gsm8k | 3.0|flexible-extract| 5|exact_match |↑ | 0.7801|± |0.0114|
|
70 |
| | |strict-match | 5|exact_match |↑ | 0.7809|± |0.0114|
|
71 |
|truthfulqa_mc2 | 2.0|none | 0|acc |↑ | 0.5389|± |0.0150|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
|
|
|
|
|
|
|
|
2 |
language:
|
3 |
- en
|
4 |
- zh
|
5 |
+
license: llama3.1
|
6 |
+
library_name: transformers
|
7 |
tags:
|
8 |
- not-for-all-audiences
|
9 |
+
datasets:
|
10 |
+
- Locutusque/hercules-v6.1
|
11 |
+
pipeline_tag: text-generation
|
12 |
+
model-index:
|
13 |
+
- name: Hercules-6.1-Llama-3.1-8B
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
type: text-generation
|
17 |
+
name: Text Generation
|
18 |
+
dataset:
|
19 |
+
name: IFEval (0-Shot)
|
20 |
+
type: HuggingFaceH4/ifeval
|
21 |
+
args:
|
22 |
+
num_few_shot: 0
|
23 |
+
metrics:
|
24 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
25 |
+
value: 60.07
|
26 |
+
name: strict accuracy
|
27 |
+
source:
|
28 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
|
29 |
+
name: Open LLM Leaderboard
|
30 |
+
- task:
|
31 |
+
type: text-generation
|
32 |
+
name: Text Generation
|
33 |
+
dataset:
|
34 |
+
name: BBH (3-Shot)
|
35 |
+
type: BBH
|
36 |
+
args:
|
37 |
+
num_few_shot: 3
|
38 |
+
metrics:
|
39 |
+
- type: acc_norm
|
40 |
+
value: 24.15
|
41 |
+
name: normalized accuracy
|
42 |
+
source:
|
43 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
|
44 |
+
name: Open LLM Leaderboard
|
45 |
+
- task:
|
46 |
+
type: text-generation
|
47 |
+
name: Text Generation
|
48 |
+
dataset:
|
49 |
+
name: MATH Lvl 5 (4-Shot)
|
50 |
+
type: hendrycks/competition_math
|
51 |
+
args:
|
52 |
+
num_few_shot: 4
|
53 |
+
metrics:
|
54 |
+
- type: exact_match
|
55 |
+
value: 15.63
|
56 |
+
name: exact match
|
57 |
+
source:
|
58 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
|
59 |
+
name: Open LLM Leaderboard
|
60 |
+
- task:
|
61 |
+
type: text-generation
|
62 |
+
name: Text Generation
|
63 |
+
dataset:
|
64 |
+
name: GPQA (0-shot)
|
65 |
+
type: Idavidrein/gpqa
|
66 |
+
args:
|
67 |
+
num_few_shot: 0
|
68 |
+
metrics:
|
69 |
+
- type: acc_norm
|
70 |
+
value: 1.45
|
71 |
+
name: acc_norm
|
72 |
+
source:
|
73 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
|
74 |
+
name: Open LLM Leaderboard
|
75 |
+
- task:
|
76 |
+
type: text-generation
|
77 |
+
name: Text Generation
|
78 |
+
dataset:
|
79 |
+
name: MuSR (0-shot)
|
80 |
+
type: TAUR-Lab/MuSR
|
81 |
+
args:
|
82 |
+
num_few_shot: 0
|
83 |
+
metrics:
|
84 |
+
- type: acc_norm
|
85 |
+
value: 3.42
|
86 |
+
name: acc_norm
|
87 |
+
source:
|
88 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
|
89 |
+
name: Open LLM Leaderboard
|
90 |
+
- task:
|
91 |
+
type: text-generation
|
92 |
+
name: Text Generation
|
93 |
+
dataset:
|
94 |
+
name: MMLU-PRO (5-shot)
|
95 |
+
type: TIGER-Lab/MMLU-Pro
|
96 |
+
config: main
|
97 |
+
split: test
|
98 |
+
args:
|
99 |
+
num_few_shot: 5
|
100 |
+
metrics:
|
101 |
+
- type: acc
|
102 |
+
value: 29.65
|
103 |
+
name: accuracy
|
104 |
+
source:
|
105 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
|
106 |
+
name: Open LLM Leaderboard
|
107 |
---
|
108 |
# Model Card: Locutusque/Hercules-6.1-Llama-3.1-8B
|
109 |
|
|
|
164 |
|gsm8k | 3.0|flexible-extract| 5|exact_match |↑ | 0.7801|± |0.0114|
|
165 |
| | |strict-match | 5|exact_match |↑ | 0.7809|± |0.0114|
|
166 |
|truthfulqa_mc2 | 2.0|none | 0|acc |↑ | 0.5389|± |0.0150|
|
167 |
+
|
168 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
169 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Locutusque__Hercules-6.1-Llama-3.1-8B)
|
170 |
+
|
171 |
+
| Metric |Value|
|
172 |
+
|-------------------|----:|
|
173 |
+
|Avg. |22.40|
|
174 |
+
|IFEval (0-Shot) |60.07|
|
175 |
+
|BBH (3-Shot) |24.15|
|
176 |
+
|MATH Lvl 5 (4-Shot)|15.63|
|
177 |
+
|GPQA (0-shot) | 1.45|
|
178 |
+
|MuSR (0-shot) | 3.42|
|
179 |
+
|MMLU-PRO (5-shot) |29.65|
|
180 |
+
|