Commit
•
b034f6d
1
Parent(s):
e6a3d63
Adding Evaluation Results (#4)
Browse files- Adding Evaluation Results (4f88c90c1e4bd0b83848815d30eccc4c612c5c05)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
@@ -111,6 +111,98 @@ model-index:
|
|
111 |
source:
|
112 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-7b
|
113 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
---
|
115 |
|
116 |
# L-MChat-7b
|
@@ -190,3 +282,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
190 |
|Winogrande (5-shot) |81.37|
|
191 |
|GSM8k (5-shot) |69.45|
|
192 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
111 |
source:
|
112 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-7b
|
113 |
name: Open LLM Leaderboard
|
114 |
+
- task:
|
115 |
+
type: text-generation
|
116 |
+
name: Text Generation
|
117 |
+
dataset:
|
118 |
+
name: IFEval (0-Shot)
|
119 |
+
type: HuggingFaceH4/ifeval
|
120 |
+
args:
|
121 |
+
num_few_shot: 0
|
122 |
+
metrics:
|
123 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
124 |
+
value: 52.97
|
125 |
+
name: strict accuracy
|
126 |
+
source:
|
127 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Artples/L-MChat-7b
|
128 |
+
name: Open LLM Leaderboard
|
129 |
+
- task:
|
130 |
+
type: text-generation
|
131 |
+
name: Text Generation
|
132 |
+
dataset:
|
133 |
+
name: BBH (3-Shot)
|
134 |
+
type: BBH
|
135 |
+
args:
|
136 |
+
num_few_shot: 3
|
137 |
+
metrics:
|
138 |
+
- type: acc_norm
|
139 |
+
value: 24.2
|
140 |
+
name: normalized accuracy
|
141 |
+
source:
|
142 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Artples/L-MChat-7b
|
143 |
+
name: Open LLM Leaderboard
|
144 |
+
- task:
|
145 |
+
type: text-generation
|
146 |
+
name: Text Generation
|
147 |
+
dataset:
|
148 |
+
name: MATH Lvl 5 (4-Shot)
|
149 |
+
type: hendrycks/competition_math
|
150 |
+
args:
|
151 |
+
num_few_shot: 4
|
152 |
+
metrics:
|
153 |
+
- type: exact_match
|
154 |
+
value: 7.93
|
155 |
+
name: exact match
|
156 |
+
source:
|
157 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Artples/L-MChat-7b
|
158 |
+
name: Open LLM Leaderboard
|
159 |
+
- task:
|
160 |
+
type: text-generation
|
161 |
+
name: Text Generation
|
162 |
+
dataset:
|
163 |
+
name: GPQA (0-shot)
|
164 |
+
type: Idavidrein/gpqa
|
165 |
+
args:
|
166 |
+
num_few_shot: 0
|
167 |
+
metrics:
|
168 |
+
- type: acc_norm
|
169 |
+
value: 7.38
|
170 |
+
name: acc_norm
|
171 |
+
source:
|
172 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Artples/L-MChat-7b
|
173 |
+
name: Open LLM Leaderboard
|
174 |
+
- task:
|
175 |
+
type: text-generation
|
176 |
+
name: Text Generation
|
177 |
+
dataset:
|
178 |
+
name: MuSR (0-shot)
|
179 |
+
type: TAUR-Lab/MuSR
|
180 |
+
args:
|
181 |
+
num_few_shot: 0
|
182 |
+
metrics:
|
183 |
+
- type: acc_norm
|
184 |
+
value: 8.12
|
185 |
+
name: acc_norm
|
186 |
+
source:
|
187 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Artples/L-MChat-7b
|
188 |
+
name: Open LLM Leaderboard
|
189 |
+
- task:
|
190 |
+
type: text-generation
|
191 |
+
name: Text Generation
|
192 |
+
dataset:
|
193 |
+
name: MMLU-PRO (5-shot)
|
194 |
+
type: TIGER-Lab/MMLU-Pro
|
195 |
+
config: main
|
196 |
+
split: test
|
197 |
+
args:
|
198 |
+
num_few_shot: 5
|
199 |
+
metrics:
|
200 |
+
- type: acc
|
201 |
+
value: 25.54
|
202 |
+
name: accuracy
|
203 |
+
source:
|
204 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Artples/L-MChat-7b
|
205 |
+
name: Open LLM Leaderboard
|
206 |
---
|
207 |
|
208 |
# L-MChat-7b
|
|
|
282 |
|Winogrande (5-shot) |81.37|
|
283 |
|GSM8k (5-shot) |69.45|
|
284 |
|
285 |
+
|
286 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
287 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Artples__L-MChat-7b)
|
288 |
+
|
289 |
+
| Metric |Value|
|
290 |
+
|-------------------|----:|
|
291 |
+
|Avg. |21.02|
|
292 |
+
|IFEval (0-Shot) |52.97|
|
293 |
+
|BBH (3-Shot) |24.20|
|
294 |
+
|MATH Lvl 5 (4-Shot)| 7.93|
|
295 |
+
|GPQA (0-shot) | 7.38|
|
296 |
+
|MuSR (0-shot) | 8.12|
|
297 |
+
|MMLU-PRO (5-shot) |25.54|
|
298 |
+
|