rohansampath commited on
Commit
dfececa
·
verified ·
1 Parent(s): 2010e21

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -3
app.py CHANGED
@@ -151,9 +151,11 @@ def enhanced_format_preview_for_display(preview_data):
151
  # 3. Gradio Interface
152
  # ---------------------------------------------------------------------------
153
  with gr.Blocks() as demo:
154
- gr.Markdown("# Mistral-7B Evaluation Demo")
155
  gr.Markdown("""
156
- This demo evaluates [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on various benchmark datasets.
 
 
157
  """)
158
 
159
  # Dataset Selection Section
@@ -164,7 +166,7 @@ with gr.Blocks() as demo:
164
  choices=["(Select Dataset)", "MMLU-Pro"],
165
  value="(Select Dataset)",
166
  label="Dataset",
167
- info="Select a dataset to evaluate the model on"
168
  )
169
  preview_toggle = gr.Button("Show Preview", interactive=False, variant="secondary")
170
 
 
151
  # 3. Gradio Interface
152
  # ---------------------------------------------------------------------------
153
  with gr.Blocks() as demo:
154
+ gr.Markdown("# Head-to-Head Model Evaluation Comparator")
155
  gr.Markdown("""
156
+ This demo evaluates two models (or one model with two different configs) on a benchmark dataset.
157
+ Available Datasets:[MMLU-Pro](https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro)
158
+ Available Models: [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
159
  """)
160
 
161
  # Dataset Selection Section
 
166
  choices=["(Select Dataset)", "MMLU-Pro"],
167
  value="(Select Dataset)",
168
  label="Dataset",
169
+ info="Select a dataset to perform the Head to Head Evaluation on. Available Datasets: [MMLU-Pro](https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro)"
170
  )
171
  preview_toggle = gr.Button("Show Preview", interactive=False, variant="secondary")
172