Commit
•
1753d6b
1
Parent(s):
9eb89de
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (09a85fab84f5a5868edab0f75b23c456d380320c)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
@@ -1,15 +1,109 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
2 |
base_model:
|
3 |
- bunnycore/Llama-3.1-8B-TitanFusion
|
4 |
- grimjim/Llama-3-Instruct-abliteration-LoRA-8B
|
5 |
- bunnycore/Llama-3.1-8B-TitanFusion-v3
|
6 |
- bunnycore/Llama-3.1-8B-TitanFusion-v2
|
7 |
- bunnycore/Llama-3.1-8B-TitanFusion
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
# merge
|
15 |
|
@@ -43,3 +137,17 @@ int8_mask: true
|
|
43 |
dtype: bfloat16
|
44 |
|
45 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- mergekit
|
5 |
+
- merge
|
6 |
base_model:
|
7 |
- bunnycore/Llama-3.1-8B-TitanFusion
|
8 |
- grimjim/Llama-3-Instruct-abliteration-LoRA-8B
|
9 |
- bunnycore/Llama-3.1-8B-TitanFusion-v3
|
10 |
- bunnycore/Llama-3.1-8B-TitanFusion-v2
|
11 |
- bunnycore/Llama-3.1-8B-TitanFusion
|
12 |
+
model-index:
|
13 |
+
- name: Llama-3.1-8B-TitanFusion-Mix
|
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: 49.25
|
26 |
+
name: strict accuracy
|
27 |
+
source:
|
28 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-Mix
|
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: 39.54
|
41 |
+
name: normalized accuracy
|
42 |
+
source:
|
43 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-Mix
|
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: 11.4
|
56 |
+
name: exact match
|
57 |
+
source:
|
58 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-Mix
|
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: 6.04
|
71 |
+
name: acc_norm
|
72 |
+
source:
|
73 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-Mix
|
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: 12.46
|
86 |
+
name: acc_norm
|
87 |
+
source:
|
88 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-Mix
|
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: 29.95
|
103 |
+
name: accuracy
|
104 |
+
source:
|
105 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-Mix
|
106 |
+
name: Open LLM Leaderboard
|
107 |
---
|
108 |
# merge
|
109 |
|
|
|
137 |
dtype: bfloat16
|
138 |
|
139 |
```
|
140 |
+
|
141 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
142 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_bunnycore__Llama-3.1-8B-TitanFusion-Mix)
|
143 |
+
|
144 |
+
| Metric |Value|
|
145 |
+
|-------------------|----:|
|
146 |
+
|Avg. |24.77|
|
147 |
+
|IFEval (0-Shot) |49.25|
|
148 |
+
|BBH (3-Shot) |39.54|
|
149 |
+
|MATH Lvl 5 (4-Shot)|11.40|
|
150 |
+
|GPQA (0-shot) | 6.04|
|
151 |
+
|MuSR (0-shot) |12.46|
|
152 |
+
|MMLU-PRO (5-shot) |29.95|
|
153 |
+
|