Commit
•
cf75a89
1
Parent(s):
476cd2a
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
@@ -106,6 +106,98 @@ model-index:
|
|
106 |
source:
|
107 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/CarbonBeagle-11B-truthy
|
108 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
109 |
---
|
110 |
|
111 |
|
@@ -122,3 +214,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
122 |
|Winogrande (5-shot) |83.82|
|
123 |
|GSM8k (5-shot) |66.11|
|
124 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
source:
|
107 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/CarbonBeagle-11B-truthy
|
108 |
name: Open LLM Leaderboard
|
109 |
+
- task:
|
110 |
+
type: text-generation
|
111 |
+
name: Text Generation
|
112 |
+
dataset:
|
113 |
+
name: IFEval (0-Shot)
|
114 |
+
type: HuggingFaceH4/ifeval
|
115 |
+
args:
|
116 |
+
num_few_shot: 0
|
117 |
+
metrics:
|
118 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
119 |
+
value: 52.12
|
120 |
+
name: strict accuracy
|
121 |
+
source:
|
122 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/CarbonBeagle-11B-truthy
|
123 |
+
name: Open LLM Leaderboard
|
124 |
+
- task:
|
125 |
+
type: text-generation
|
126 |
+
name: Text Generation
|
127 |
+
dataset:
|
128 |
+
name: BBH (3-Shot)
|
129 |
+
type: BBH
|
130 |
+
args:
|
131 |
+
num_few_shot: 3
|
132 |
+
metrics:
|
133 |
+
- type: acc_norm
|
134 |
+
value: 33.99
|
135 |
+
name: normalized accuracy
|
136 |
+
source:
|
137 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/CarbonBeagle-11B-truthy
|
138 |
+
name: Open LLM Leaderboard
|
139 |
+
- task:
|
140 |
+
type: text-generation
|
141 |
+
name: Text Generation
|
142 |
+
dataset:
|
143 |
+
name: MATH Lvl 5 (4-Shot)
|
144 |
+
type: hendrycks/competition_math
|
145 |
+
args:
|
146 |
+
num_few_shot: 4
|
147 |
+
metrics:
|
148 |
+
- type: exact_match
|
149 |
+
value: 4.76
|
150 |
+
name: exact match
|
151 |
+
source:
|
152 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/CarbonBeagle-11B-truthy
|
153 |
+
name: Open LLM Leaderboard
|
154 |
+
- task:
|
155 |
+
type: text-generation
|
156 |
+
name: Text Generation
|
157 |
+
dataset:
|
158 |
+
name: GPQA (0-shot)
|
159 |
+
type: Idavidrein/gpqa
|
160 |
+
args:
|
161 |
+
num_few_shot: 0
|
162 |
+
metrics:
|
163 |
+
- type: acc_norm
|
164 |
+
value: 6.6
|
165 |
+
name: acc_norm
|
166 |
+
source:
|
167 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/CarbonBeagle-11B-truthy
|
168 |
+
name: Open LLM Leaderboard
|
169 |
+
- task:
|
170 |
+
type: text-generation
|
171 |
+
name: Text Generation
|
172 |
+
dataset:
|
173 |
+
name: MuSR (0-shot)
|
174 |
+
type: TAUR-Lab/MuSR
|
175 |
+
args:
|
176 |
+
num_few_shot: 0
|
177 |
+
metrics:
|
178 |
+
- type: acc_norm
|
179 |
+
value: 4.11
|
180 |
+
name: acc_norm
|
181 |
+
source:
|
182 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/CarbonBeagle-11B-truthy
|
183 |
+
name: Open LLM Leaderboard
|
184 |
+
- task:
|
185 |
+
type: text-generation
|
186 |
+
name: Text Generation
|
187 |
+
dataset:
|
188 |
+
name: MMLU-PRO (5-shot)
|
189 |
+
type: TIGER-Lab/MMLU-Pro
|
190 |
+
config: main
|
191 |
+
split: test
|
192 |
+
args:
|
193 |
+
num_few_shot: 5
|
194 |
+
metrics:
|
195 |
+
- type: acc
|
196 |
+
value: 26.19
|
197 |
+
name: accuracy
|
198 |
+
source:
|
199 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/CarbonBeagle-11B-truthy
|
200 |
+
name: Open LLM Leaderboard
|
201 |
---
|
202 |
|
203 |
|
|
|
214 |
|Winogrande (5-shot) |83.82|
|
215 |
|GSM8k (5-shot) |66.11|
|
216 |
|
217 |
+
|
218 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
219 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__CarbonBeagle-11B-truthy)
|
220 |
+
|
221 |
+
| Metric |Value|
|
222 |
+
|-------------------|----:|
|
223 |
+
|Avg. |21.29|
|
224 |
+
|IFEval (0-Shot) |52.12|
|
225 |
+
|BBH (3-Shot) |33.99|
|
226 |
+
|MATH Lvl 5 (4-Shot)| 4.76|
|
227 |
+
|GPQA (0-shot) | 6.60|
|
228 |
+
|MuSR (0-shot) | 4.11|
|
229 |
+
|MMLU-PRO (5-shot) |26.19|
|
230 |
+
|