Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -1,9 +1,104 @@
|
|
1 |
---
|
|
|
2 |
library_name: transformers
|
3 |
tags:
|
4 |
- mergekit
|
5 |
- merge
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
---
|
8 |
# Llama-3.1-SuperNova-Lite_TIES_with_Base
|
9 |
|
@@ -51,4 +146,17 @@ parameters:
|
|
51 |
int8_mask: true
|
52 |
dtype: bfloat16
|
53 |
|
54 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: llama3.1
|
3 |
library_name: transformers
|
4 |
tags:
|
5 |
- mergekit
|
6 |
- merge
|
7 |
+
model-index:
|
8 |
+
- name: Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
|
9 |
+
results:
|
10 |
+
- task:
|
11 |
+
type: text-generation
|
12 |
+
name: Text Generation
|
13 |
+
dataset:
|
14 |
+
name: IFEval (0-Shot)
|
15 |
+
type: HuggingFaceH4/ifeval
|
16 |
+
args:
|
17 |
+
num_few_shot: 0
|
18 |
+
metrics:
|
19 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
20 |
+
value: 80.96
|
21 |
+
name: strict accuracy
|
22 |
+
source:
|
23 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
|
24 |
+
name: Open LLM Leaderboard
|
25 |
+
- task:
|
26 |
+
type: text-generation
|
27 |
+
name: Text Generation
|
28 |
+
dataset:
|
29 |
+
name: BBH (3-Shot)
|
30 |
+
type: BBH
|
31 |
+
args:
|
32 |
+
num_few_shot: 3
|
33 |
+
metrics:
|
34 |
+
- type: acc_norm
|
35 |
+
value: 31.47
|
36 |
+
name: normalized accuracy
|
37 |
+
source:
|
38 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
|
39 |
+
name: Open LLM Leaderboard
|
40 |
+
- task:
|
41 |
+
type: text-generation
|
42 |
+
name: Text Generation
|
43 |
+
dataset:
|
44 |
+
name: MATH Lvl 5 (4-Shot)
|
45 |
+
type: hendrycks/competition_math
|
46 |
+
args:
|
47 |
+
num_few_shot: 4
|
48 |
+
metrics:
|
49 |
+
- type: exact_match
|
50 |
+
value: 15.56
|
51 |
+
name: exact match
|
52 |
+
source:
|
53 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
|
54 |
+
name: Open LLM Leaderboard
|
55 |
+
- task:
|
56 |
+
type: text-generation
|
57 |
+
name: Text Generation
|
58 |
+
dataset:
|
59 |
+
name: GPQA (0-shot)
|
60 |
+
type: Idavidrein/gpqa
|
61 |
+
args:
|
62 |
+
num_few_shot: 0
|
63 |
+
metrics:
|
64 |
+
- type: acc_norm
|
65 |
+
value: 7.94
|
66 |
+
name: acc_norm
|
67 |
+
source:
|
68 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
|
69 |
+
name: Open LLM Leaderboard
|
70 |
+
- task:
|
71 |
+
type: text-generation
|
72 |
+
name: Text Generation
|
73 |
+
dataset:
|
74 |
+
name: MuSR (0-shot)
|
75 |
+
type: TAUR-Lab/MuSR
|
76 |
+
args:
|
77 |
+
num_few_shot: 0
|
78 |
+
metrics:
|
79 |
+
- type: acc_norm
|
80 |
+
value: 10.74
|
81 |
+
name: acc_norm
|
82 |
+
source:
|
83 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
|
84 |
+
name: Open LLM Leaderboard
|
85 |
+
- task:
|
86 |
+
type: text-generation
|
87 |
+
name: Text Generation
|
88 |
+
dataset:
|
89 |
+
name: MMLU-PRO (5-shot)
|
90 |
+
type: TIGER-Lab/MMLU-Pro
|
91 |
+
config: main
|
92 |
+
split: test
|
93 |
+
args:
|
94 |
+
num_few_shot: 5
|
95 |
+
metrics:
|
96 |
+
- type: acc
|
97 |
+
value: 32.01
|
98 |
+
name: accuracy
|
99 |
+
source:
|
100 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
|
101 |
+
name: Open LLM Leaderboard
|
102 |
---
|
103 |
# Llama-3.1-SuperNova-Lite_TIES_with_Base
|
104 |
|
|
|
146 |
int8_mask: true
|
147 |
dtype: bfloat16
|
148 |
|
149 |
+
```
|
150 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
151 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Joseph717171__Llama-3.1-SuperNova-8B-Lite_TIES_with_Base)
|
152 |
+
|
153 |
+
| Metric |Value|
|
154 |
+
|-------------------|----:|
|
155 |
+
|Avg. |29.78|
|
156 |
+
|IFEval (0-Shot) |80.96|
|
157 |
+
|BBH (3-Shot) |31.47|
|
158 |
+
|MATH Lvl 5 (4-Shot)|15.56|
|
159 |
+
|GPQA (0-shot) | 7.94|
|
160 |
+
|MuSR (0-shot) |10.74|
|
161 |
+
|MMLU-PRO (5-shot) |32.01|
|
162 |
+
|