Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,8 @@ model-index:
|
|
16 |
value: 72.05
|
17 |
name: averaged accuracy
|
18 |
source:
|
19 |
-
url:
|
|
|
20 |
name: Open LLM Leaderboard
|
21 |
- task:
|
22 |
type: text-generation
|
@@ -32,7 +33,8 @@ model-index:
|
|
32 |
value: 30.85
|
33 |
name: normalized accuracy
|
34 |
source:
|
35 |
-
url:
|
|
|
36 |
name: Open LLM Leaderboard
|
37 |
- task:
|
38 |
type: text-generation
|
@@ -48,7 +50,8 @@ model-index:
|
|
48 |
value: 7.02
|
49 |
name: exact match
|
50 |
source:
|
51 |
-
url:
|
|
|
52 |
name: Open LLM Leaderboard
|
53 |
- task:
|
54 |
type: text-generation
|
@@ -64,7 +67,8 @@ model-index:
|
|
64 |
value: 7.38
|
65 |
name: acc_norm
|
66 |
source:
|
67 |
-
url:
|
|
|
68 |
name: Open LLM Leaderboard
|
69 |
- task:
|
70 |
type: text-generation
|
@@ -79,7 +83,8 @@ model-index:
|
|
79 |
value: 6.15
|
80 |
name: acc_norm
|
81 |
source:
|
82 |
-
url:
|
|
|
83 |
name: Open LLM Leaderboard
|
84 |
- task:
|
85 |
type: text-generation
|
@@ -96,8 +101,11 @@ model-index:
|
|
96 |
value: 30.37
|
97 |
name: accuracy
|
98 |
source:
|
99 |
-
url:
|
|
|
100 |
name: Open LLM Leaderboard
|
|
|
|
|
101 |
---
|
102 |
<p align="center" width="100%">
|
103 |
</p>
|
@@ -526,5 +534,4 @@ Summarized results can be found [here](https://huggingface.co/datasets/open-llm-
|
|
526 |
|MATH Lvl 5 (4-Shot)| 7.02|
|
527 |
|GPQA (0-shot) | 7.38|
|
528 |
|MuSR (0-shot) | 6.15|
|
529 |
-
|MMLU-PRO (5-shot) | 30.37|
|
530 |
-
|
|
|
16 |
value: 72.05
|
17 |
name: averaged accuracy
|
18 |
source:
|
19 |
+
url: >-
|
20 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
|
21 |
name: Open LLM Leaderboard
|
22 |
- task:
|
23 |
type: text-generation
|
|
|
33 |
value: 30.85
|
34 |
name: normalized accuracy
|
35 |
source:
|
36 |
+
url: >-
|
37 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
|
38 |
name: Open LLM Leaderboard
|
39 |
- task:
|
40 |
type: text-generation
|
|
|
50 |
value: 7.02
|
51 |
name: exact match
|
52 |
source:
|
53 |
+
url: >-
|
54 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
|
55 |
name: Open LLM Leaderboard
|
56 |
- task:
|
57 |
type: text-generation
|
|
|
67 |
value: 7.38
|
68 |
name: acc_norm
|
69 |
source:
|
70 |
+
url: >-
|
71 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
|
72 |
name: Open LLM Leaderboard
|
73 |
- task:
|
74 |
type: text-generation
|
|
|
83 |
value: 6.15
|
84 |
name: acc_norm
|
85 |
source:
|
86 |
+
url: >-
|
87 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
|
88 |
name: Open LLM Leaderboard
|
89 |
- task:
|
90 |
type: text-generation
|
|
|
101 |
value: 30.37
|
102 |
name: accuracy
|
103 |
source:
|
104 |
+
url: >-
|
105 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=FuseAI%2FFuseChat-Llama-3.1-8B-Instruct
|
106 |
name: Open LLM Leaderboard
|
107 |
+
datasets:
|
108 |
+
- FuseAI/FuseChat-3.0-DPO-Data
|
109 |
---
|
110 |
<p align="center" width="100%">
|
111 |
</p>
|
|
|
534 |
|MATH Lvl 5 (4-Shot)| 7.02|
|
535 |
|GPQA (0-shot) | 7.38|
|
536 |
|MuSR (0-shot) | 6.15|
|
537 |
+
|MMLU-PRO (5-shot) | 30.37|
|
|