Hugging Face's logo

djuna
/
Q2.5-Veltha-14B

Text Generation
Transformers
Safetensors
qwen2
mergekit
Merge
conversational
Eval Results
text-generation-inference
Model card Files
xet
Community
2
djuna commited on
Commit
076f3ed
·
verified ·
1 Parent(s): 797d193

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -8
README.md CHANGED
@@ -26,7 +26,8 @@ model-index:
26
  value: 82.92
27
  name: strict accuracy
28
  source:
29
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
 
30
  name: Open LLM Leaderboard
31
  - task:
32
  type: text-generation
@@ -41,7 +42,8 @@ model-index:
41
  value: 49.75
42
  name: normalized accuracy
43
  source:
44
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
 
45
  name: Open LLM Leaderboard
46
  - task:
47
  type: text-generation
@@ -56,7 +58,8 @@ model-index:
56
  value: 28.02
57
  name: exact match
58
  source:
59
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
 
60
  name: Open LLM Leaderboard
61
  - task:
62
  type: text-generation
@@ -71,7 +74,8 @@ model-index:
71
  value: 14.54
72
  name: acc_norm
73
  source:
74
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
 
75
  name: Open LLM Leaderboard
76
  - task:
77
  type: text-generation
@@ -86,7 +90,8 @@ model-index:
86
  value: 12.26
87
  name: acc_norm
88
  source:
89
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
 
90
  name: Open LLM Leaderboard
91
  - task:
92
  type: text-generation
@@ -103,8 +108,10 @@ model-index:
103
  value: 47.76
104
  name: accuracy
105
  source:
106
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
 
107
  name: Open LLM Leaderboard
 
108
  ---
109
  # merge
110
 
@@ -172,5 +179,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
172
  |MATH Lvl 5 (4-Shot)|28.02|
173
  |GPQA (0-shot) |14.54|
174
  |MuSR (0-shot) |12.26|
175
- |MMLU-PRO (5-shot) |47.76|
176
-
 
26
  value: 82.92
27
  name: strict accuracy
28
  source:
29
+ url: >-
30
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
31
  name: Open LLM Leaderboard
32
  - task:
33
  type: text-generation
 
42
  value: 49.75
43
  name: normalized accuracy
44
  source:
45
+ url: >-
46
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
47
  name: Open LLM Leaderboard
48
  - task:
49
  type: text-generation
 
58
  value: 28.02
59
  name: exact match
60
  source:
61
+ url: >-
62
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
63
  name: Open LLM Leaderboard
64
  - task:
65
  type: text-generation
 
74
  value: 14.54
75
  name: acc_norm
76
  source:
77
+ url: >-
78
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
79
  name: Open LLM Leaderboard
80
  - task:
81
  type: text-generation
 
90
  value: 12.26
91
  name: acc_norm
92
  source:
93
+ url: >-
94
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
95
  name: Open LLM Leaderboard
96
  - task:
97
  type: text-generation
 
108
  value: 47.76
109
  name: accuracy
110
  source:
111
+ url: >-
112
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
113
  name: Open LLM Leaderboard
114
+ new_version: djuna/Q2.5-Veltha-14B-0.5
115
  ---
116
  # merge
117
 
 
179
  |MATH Lvl 5 (4-Shot)|28.02|
180
  |GPQA (0-shot) |14.54|
181
  |MuSR (0-shot) |12.26|
182
+ |MMLU-PRO (5-shot) |47.76|