Adding Evaluation Results (#5)
Browse files- Adding Evaluation Results (a62f09936d649d76c38085bc7070f6ce4a8d6654)
README.md
CHANGED
@@ -1,9 +1,112 @@
|
|
1 |
---
|
2 |
license: other
|
3 |
-
license_name: microsoft-research-license
|
4 |
tags:
|
5 |
- merge
|
6 |
- not-for-all-audiences
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
---
|
8 |
# DarkForest 20B v2.0
|
9 |
|
@@ -33,4 +136,17 @@ tags:
|
|
33 |
- This is NOT Harry Potter level storytelling.
|
34 |
|
35 |
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:
|
36 |
-
<a href="https://www.buymeacoffee.com/TeeZee" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: other
|
|
|
3 |
tags:
|
4 |
- merge
|
5 |
- not-for-all-audiences
|
6 |
+
license_name: microsoft-research-license
|
7 |
+
model-index:
|
8 |
+
- name: DarkForest-20B-v2.0
|
9 |
+
results:
|
10 |
+
- task:
|
11 |
+
type: text-generation
|
12 |
+
name: Text Generation
|
13 |
+
dataset:
|
14 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
15 |
+
type: ai2_arc
|
16 |
+
config: ARC-Challenge
|
17 |
+
split: test
|
18 |
+
args:
|
19 |
+
num_few_shot: 25
|
20 |
+
metrics:
|
21 |
+
- type: acc_norm
|
22 |
+
value: 63.74
|
23 |
+
name: normalized accuracy
|
24 |
+
source:
|
25 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
|
26 |
+
name: Open LLM Leaderboard
|
27 |
+
- task:
|
28 |
+
type: text-generation
|
29 |
+
name: Text Generation
|
30 |
+
dataset:
|
31 |
+
name: HellaSwag (10-Shot)
|
32 |
+
type: hellaswag
|
33 |
+
split: validation
|
34 |
+
args:
|
35 |
+
num_few_shot: 10
|
36 |
+
metrics:
|
37 |
+
- type: acc_norm
|
38 |
+
value: 86.32
|
39 |
+
name: normalized accuracy
|
40 |
+
source:
|
41 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
|
42 |
+
name: Open LLM Leaderboard
|
43 |
+
- task:
|
44 |
+
type: text-generation
|
45 |
+
name: Text Generation
|
46 |
+
dataset:
|
47 |
+
name: MMLU (5-Shot)
|
48 |
+
type: cais/mmlu
|
49 |
+
config: all
|
50 |
+
split: test
|
51 |
+
args:
|
52 |
+
num_few_shot: 5
|
53 |
+
metrics:
|
54 |
+
- type: acc
|
55 |
+
value: 59.79
|
56 |
+
name: accuracy
|
57 |
+
source:
|
58 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
|
59 |
+
name: Open LLM Leaderboard
|
60 |
+
- task:
|
61 |
+
type: text-generation
|
62 |
+
name: Text Generation
|
63 |
+
dataset:
|
64 |
+
name: TruthfulQA (0-shot)
|
65 |
+
type: truthful_qa
|
66 |
+
config: multiple_choice
|
67 |
+
split: validation
|
68 |
+
args:
|
69 |
+
num_few_shot: 0
|
70 |
+
metrics:
|
71 |
+
- type: mc2
|
72 |
+
value: 56.14
|
73 |
+
source:
|
74 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
|
75 |
+
name: Open LLM Leaderboard
|
76 |
+
- task:
|
77 |
+
type: text-generation
|
78 |
+
name: Text Generation
|
79 |
+
dataset:
|
80 |
+
name: Winogrande (5-shot)
|
81 |
+
type: winogrande
|
82 |
+
config: winogrande_xl
|
83 |
+
split: validation
|
84 |
+
args:
|
85 |
+
num_few_shot: 5
|
86 |
+
metrics:
|
87 |
+
- type: acc
|
88 |
+
value: 77.9
|
89 |
+
name: accuracy
|
90 |
+
source:
|
91 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
|
92 |
+
name: Open LLM Leaderboard
|
93 |
+
- task:
|
94 |
+
type: text-generation
|
95 |
+
name: Text Generation
|
96 |
+
dataset:
|
97 |
+
name: GSM8k (5-shot)
|
98 |
+
type: gsm8k
|
99 |
+
config: main
|
100 |
+
split: test
|
101 |
+
args:
|
102 |
+
num_few_shot: 5
|
103 |
+
metrics:
|
104 |
+
- type: acc
|
105 |
+
value: 23.28
|
106 |
+
name: accuracy
|
107 |
+
source:
|
108 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
|
109 |
+
name: Open LLM Leaderboard
|
110 |
---
|
111 |
# DarkForest 20B v2.0
|
112 |
|
|
|
136 |
- This is NOT Harry Potter level storytelling.
|
137 |
|
138 |
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:
|
139 |
+
<a href="https://www.buymeacoffee.com/TeeZee" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
|
140 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
141 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TeeZee__DarkForest-20B-v2.0)
|
142 |
+
|
143 |
+
| Metric |Value|
|
144 |
+
|---------------------------------|----:|
|
145 |
+
|Avg. |61.19|
|
146 |
+
|AI2 Reasoning Challenge (25-Shot)|63.74|
|
147 |
+
|HellaSwag (10-Shot) |86.32|
|
148 |
+
|MMLU (5-Shot) |59.79|
|
149 |
+
|TruthfulQA (0-shot) |56.14|
|
150 |
+
|Winogrande (5-shot) |77.90|
|
151 |
+
|GSM8k (5-shot) |23.28|
|
152 |
+
|