davanstrien HF staff commited on
Commit
f9ba57a
Β·
1 Parent(s): 161eaf7

html title

Browse files
Files changed (1) hide show
  1. app.py +8 -4
app.py CHANGED
@@ -190,11 +190,16 @@ def generate_instruction_response():
190
 
191
 
192
  title = """
193
- # πŸ¦β€β¬› Magpie Preference
194
  """
195
 
196
  description = """
197
- This demo showcases **Magpie**, an innovative approach to generating high-quality data by prompting aligned LLMs with their pre-query templates. Unlike many existing synthetic data generation methods, Magpie doesn't rely on prompt engineering or seed questions for generating synthetic data. Instead, it uses the prompt template of an aligned LLM to generate both a user query and an LLM response.
 
 
 
 
 
198
 
199
  As well as providing a demo for the Magpie generations, this Space also allows you to submit a preference rating for the generated data, contributing to a crowdsourced preference dataset!
200
 
@@ -204,7 +209,6 @@ As well as providing a demo for the Magpie generations, this Space also allows y
204
  2. **πŸ’¬ Response Generation:** The model generates a response to this instruction.
205
  3. **πŸ‘πŸ‘Ž User Feedback (optional):** Rate the quality of the generated content and contribute to a crowdsourced preference dataset for synthetic dataset.
206
 
207
-
208
  πŸ”— Find the crowd-generated dataset at [davanstrien/magpie-preference](https://huggingface.co/datasets/davanstrien/magpie-preference). It's updated every minute!
209
 
210
  πŸ“š Learn more about Magpie in the [paper](https://huggingface.co/papers/2406.08464).
@@ -214,7 +218,7 @@ As well as providing a demo for the Magpie generations, this Space also allows y
214
 
215
  # Create the Gradio interface
216
  with gr.Blocks() as iface:
217
- gr.Markdown(title)
218
  gr.Markdown(description)
219
 
220
  # Add a state variable to store the session ID
 
190
 
191
 
192
  title = """
193
+ <h1>&#x1F426; Magpie Preference</h1>
194
  """
195
 
196
  description = """
197
+ This demo showcases **[Magpie](https://magpie-align.github.io/)**, an innovative approach to generating high-quality data by prompting aligned LLMs with their pre-query templates. Unlike many existing synthetic data generation methods, Magpie doesn't rely on prompt engineering or seed questions for generating synthetic data. Instead, it uses the prompt template of an aligned LLM to generate both the user query and an LLM response.
198
+
199
+ <img src="https://magpie-align.github.io/images/pipeline.png" alt="Magpie Pipeline" width="50%" align="center" />
200
+
201
+ *Image Source: [Magpie project page](https://magpie-align.github.io/)*
202
+
203
 
204
  As well as providing a demo for the Magpie generations, this Space also allows you to submit a preference rating for the generated data, contributing to a crowdsourced preference dataset!
205
 
 
209
  2. **πŸ’¬ Response Generation:** The model generates a response to this instruction.
210
  3. **πŸ‘πŸ‘Ž User Feedback (optional):** Rate the quality of the generated content and contribute to a crowdsourced preference dataset for synthetic dataset.
211
 
 
212
  πŸ”— Find the crowd-generated dataset at [davanstrien/magpie-preference](https://huggingface.co/datasets/davanstrien/magpie-preference). It's updated every minute!
213
 
214
  πŸ“š Learn more about Magpie in the [paper](https://huggingface.co/papers/2406.08464).
 
218
 
219
  # Create the Gradio interface
220
  with gr.Blocks() as iface:
221
+ gr.HTML(title)
222
  gr.Markdown(description)
223
 
224
  # Add a state variable to store the session ID