Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -1,5 +1,14 @@
|
|
1 |
---
|
2 |
license: osl-3.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
model-index:
|
4 |
- name: indus_1.175B
|
5 |
results:
|
@@ -103,17 +112,98 @@ model-index:
|
|
103 |
source:
|
104 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nickmalhotra/indus_1.175B
|
105 |
name: Open LLM Leaderboard
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
117 |
---
|
118 |
|
119 |
# Model Card for Project Indus
|
@@ -474,4 +564,17 @@ Project Indus LLM is designed as a foundational model suitable for further devel
|
|
474 |
- **Curate Targeted Data**: Ensure the training data is relevant and of high quality to improve model performance.
|
475 |
- **Continuous Evaluation**: Regularly assess the model's performance during and after fine-tuning to maintain accuracy and reduce biases.
|
476 |
|
477 |
-
This disclaimer aims to provide users with a clear understanding of the model's capabilities and limitations, facilitating its effective application and development.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: osl-3.0
|
3 |
+
widget:
|
4 |
+
- example_title: वर्तमान प्रधानमंत्री
|
5 |
+
messages:
|
6 |
+
- role: user
|
7 |
+
content: भारत के वर्तमान प्रधानमंत्री कौन हैं?
|
8 |
+
- example_title: होली का महत्व
|
9 |
+
messages:
|
10 |
+
- role: user
|
11 |
+
content: होली का महत्व क्या है?
|
12 |
model-index:
|
13 |
- name: indus_1.175B
|
14 |
results:
|
|
|
112 |
source:
|
113 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nickmalhotra/indus_1.175B
|
114 |
name: Open LLM Leaderboard
|
115 |
+
- task:
|
116 |
+
type: text-generation
|
117 |
+
name: Text Generation
|
118 |
+
dataset:
|
119 |
+
name: IFEval (0-Shot)
|
120 |
+
type: HuggingFaceH4/ifeval
|
121 |
+
args:
|
122 |
+
num_few_shot: 0
|
123 |
+
metrics:
|
124 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
125 |
+
value: 24.4
|
126 |
+
name: strict accuracy
|
127 |
+
source:
|
128 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbrahme/IndusQ
|
129 |
+
name: Open LLM Leaderboard
|
130 |
+
- task:
|
131 |
+
type: text-generation
|
132 |
+
name: Text Generation
|
133 |
+
dataset:
|
134 |
+
name: BBH (3-Shot)
|
135 |
+
type: BBH
|
136 |
+
args:
|
137 |
+
num_few_shot: 3
|
138 |
+
metrics:
|
139 |
+
- type: acc_norm
|
140 |
+
value: 3.75
|
141 |
+
name: normalized accuracy
|
142 |
+
source:
|
143 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbrahme/IndusQ
|
144 |
+
name: Open LLM Leaderboard
|
145 |
+
- task:
|
146 |
+
type: text-generation
|
147 |
+
name: Text Generation
|
148 |
+
dataset:
|
149 |
+
name: MATH Lvl 5 (4-Shot)
|
150 |
+
type: hendrycks/competition_math
|
151 |
+
args:
|
152 |
+
num_few_shot: 4
|
153 |
+
metrics:
|
154 |
+
- type: exact_match
|
155 |
+
value: 0.0
|
156 |
+
name: exact match
|
157 |
+
source:
|
158 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbrahme/IndusQ
|
159 |
+
name: Open LLM Leaderboard
|
160 |
+
- task:
|
161 |
+
type: text-generation
|
162 |
+
name: Text Generation
|
163 |
+
dataset:
|
164 |
+
name: GPQA (0-shot)
|
165 |
+
type: Idavidrein/gpqa
|
166 |
+
args:
|
167 |
+
num_few_shot: 0
|
168 |
+
metrics:
|
169 |
+
- type: acc_norm
|
170 |
+
value: 2.01
|
171 |
+
name: acc_norm
|
172 |
+
source:
|
173 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbrahme/IndusQ
|
174 |
+
name: Open LLM Leaderboard
|
175 |
+
- task:
|
176 |
+
type: text-generation
|
177 |
+
name: Text Generation
|
178 |
+
dataset:
|
179 |
+
name: MuSR (0-shot)
|
180 |
+
type: TAUR-Lab/MuSR
|
181 |
+
args:
|
182 |
+
num_few_shot: 0
|
183 |
+
metrics:
|
184 |
+
- type: acc_norm
|
185 |
+
value: 2.25
|
186 |
+
name: acc_norm
|
187 |
+
source:
|
188 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbrahme/IndusQ
|
189 |
+
name: Open LLM Leaderboard
|
190 |
+
- task:
|
191 |
+
type: text-generation
|
192 |
+
name: Text Generation
|
193 |
+
dataset:
|
194 |
+
name: MMLU-PRO (5-shot)
|
195 |
+
type: TIGER-Lab/MMLU-Pro
|
196 |
+
config: main
|
197 |
+
split: test
|
198 |
+
args:
|
199 |
+
num_few_shot: 5
|
200 |
+
metrics:
|
201 |
+
- type: acc
|
202 |
+
value: 1.34
|
203 |
+
name: accuracy
|
204 |
+
source:
|
205 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbrahme/IndusQ
|
206 |
+
name: Open LLM Leaderboard
|
207 |
---
|
208 |
|
209 |
# Model Card for Project Indus
|
|
|
564 |
- **Curate Targeted Data**: Ensure the training data is relevant and of high quality to improve model performance.
|
565 |
- **Continuous Evaluation**: Regularly assess the model's performance during and after fine-tuning to maintain accuracy and reduce biases.
|
566 |
|
567 |
+
This disclaimer aims to provide users with a clear understanding of the model's capabilities and limitations, facilitating its effective application and development.
|
568 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
569 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nbrahme__IndusQ)
|
570 |
+
|
571 |
+
| Metric |Value|
|
572 |
+
|-------------------|----:|
|
573 |
+
|Avg. | 5.62|
|
574 |
+
|IFEval (0-Shot) |24.40|
|
575 |
+
|BBH (3-Shot) | 3.75|
|
576 |
+
|MATH Lvl 5 (4-Shot)| 0.00|
|
577 |
+
|GPQA (0-shot) | 2.01|
|
578 |
+
|MuSR (0-shot) | 2.25|
|
579 |
+
|MMLU-PRO (5-shot) | 1.34|
|
580 |
+
|