Hugging Face's logo

VAGOsolutions
/
SauerkrautLM-v2-14b-SFT

Safetensors
qwen2
spectrum
sft
Eval Results
Model card Files Community
1
DavidGF commited on
Commit
367b18e
•
1 Parent(s): 09fd821

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -6
README.md CHANGED
@@ -3,9 +3,17 @@ license: apache-2.0
3
  language:
4
  - de
5
  - en
 
 
 
 
 
 
6
  tags:
7
  - spectrum
8
  - sft
 
 
9
  ---
10
 
11
  ![SauerkrautLM-v2-14b-SFT](https://vago-solutions.ai/wp-content/uploads/2024/08/SauerkrautLM-v2-14b-SFT.png "SauerkrautLM-v2-14b-SFT")
@@ -81,22 +89,22 @@ This release marks the one-year anniversary of SauerkrautLM, showcasing our most
81
  ## Evaluation
82
 
83
  **AGIEVAL**
84
- ![SauerkrautLM-v2-14b-SFT-AGIEVAL](https://vago-solutions.ai/wp-content/uploads/2024/08/AGIeval-14b.png "SauerkrautLM-v2-14b-SFT-AGIEVAL")
85
 
86
  **GPT4ALL**
87
- ![SauerkrautLM-v2-14b-SFT-GPT4ALL](https://vago-solutions.ai/wp-content/uploads/2024/08/GPT4ALL-14b.png "SauerkrautLM-v2-14b-SFT-GPT4ALL")
88
 
89
  **TRUTHFULQA**
90
- ![SauerkrautLM-v2-14b-SFT-TRUTHFULQA](https://vago-solutions.ai/wp-content/uploads/2024/08/TQA-14b.png "SauerkrautLM-v2-14b-SFT-TRUTHFULQA")
91
 
92
  **OPENLEADERBOARD 2**
93
- ![SauerkrautLM-v2-14b-SFT-OPENLEADERBOARD](https://vago-solutions.ai/wp-content/uploads/2024/08/HF2-14b.png "SauerkrautLM-v2-14b-SFT-OPENLEADERBOARD")
94
 
95
  **MMLU 5-shot**
96
- ![SauerkrautLM-v2-14b-SFT-MMLU-5shot](https://vago-solutions.ai/wp-content/uploads/2024/08/MMLU-14b.png "SauerkrautLM-v2-14b-SFT-MMLU-5shot")
97
 
98
  **Berkeley Function Calling Leaderboard**
99
- ![SauerkrautLM-v2-14b-SFT-BERKELEY](https://vago-solutions.ai/wp-content/uploads/2024/08/Berkeley-14b.png "SauerkrautLM-v2-14b-SFT-BERKELEY")
100
 
101
  Please note that our benchmark results in absolute numbers may differ from the Hugging Face Leaderboard due to variations in benchmark evaluation pipelines. However, the relative differences remain consistent.
102
 
 
3
  language:
4
  - de
5
  - en
6
+ - it
7
+ - fr
8
+ - pt
9
+ - nl
10
+ - ar
11
+ - es
12
  tags:
13
  - spectrum
14
  - sft
15
+ base_model:
16
+ - Qwen/Qwen2.5-14B
17
  ---
18
 
19
  ![SauerkrautLM-v2-14b-SFT](https://vago-solutions.ai/wp-content/uploads/2024/08/SauerkrautLM-v2-14b-SFT.png "SauerkrautLM-v2-14b-SFT")
 
89
  ## Evaluation
90
 
91
  **AGIEVAL**
92
+ ![SauerkrautLM-v2-14b-SFT-AGIEVAL](https://vago-solutions.ai/wp-content/uploads/2024/11/AGIeval-14b-dpo.png "SauerkrautLM-v2-14b-SFT-AGIEVAL")
93
 
94
  **GPT4ALL**
95
+ ![SauerkrautLM-v2-14b-SFT-GPT4ALL](https://vago-solutions.ai/wp-content/uploads/2024/11/GPT4ALL-14b-dpo.png "SauerkrautLM-v2-14b-SFT-GPT4ALL")
96
 
97
  **TRUTHFULQA**
98
+ ![SauerkrautLM-v2-14b-SFT-TRUTHFULQA](https://vago-solutions.ai/wp-content/uploads/2024/11/TQA-14b-dpo.png "SauerkrautLM-v2-14b-SFT-TRUTHFULQA")
99
 
100
  **OPENLEADERBOARD 2**
101
+ ![SauerkrautLM-v2-14b-SFT-OPENLEADERBOARD](https://vago-solutions.ai/wp-content/uploads/2024/11/HF2-14b-dpo.png "SauerkrautLM-v2-14b-SFT-OPENLEADERBOARD")
102
 
103
  **MMLU 5-shot**
104
+ ![SauerkrautLM-v2-14b-SFT-MMLU-5shot](https://vago-solutions.ai/wp-content/uploads/2024/11/MMLU-14b-dpo.png "SauerkrautLM-v2-14b-SFT-MMLU-5shot")
105
 
106
  **Berkeley Function Calling Leaderboard**
107
+ ![SauerkrautLM-v2-14b-SFT-BERKELEY](https://vago-solutions.ai/wp-content/uploads/2024/11/Berkeley-14b-dpo.png "SauerkrautLM-v2-14b-SFT-BERKELEY")
108
 
109
  Please note that our benchmark results in absolute numbers may differ from the Hugging Face Leaderboard due to variations in benchmark evaluation pipelines. However, the relative differences remain consistent.
110