ArmelR commited on
Commit
7b6a5b3
1 Parent(s): 32241a9

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -3
app.py CHANGED
@@ -351,7 +351,7 @@ def retry_last_answer(
351
  do_save,
352
  )
353
 
354
- title = """<h1 align="center">Chat with Gradio 💬</h1>"""
355
  custom_css = """
356
  #banner-image {
357
  display: block;
@@ -384,9 +384,11 @@ with gr.Blocks(analytics_enabled=False, css=custom_css) as demo:
384
  with gr.Column():
385
  gr.Markdown(
386
  """![](https://huggingface.co/spaces/codeparrot/gradio-playground/resolve/main/gradio.png)
387
- Chat-with-Gradio is a 15.5 billion parameter language model based on [BigCode's StarCoderplus model](https://huggingface.co/bigcode/starcoderplus) that has been trained on pairs of questions and answers from [Stack Exchange](https://stackexchange.com) using Direct Preference Optimization (DPO) with the [TRL library](https://github.com/lvwerra/trl). For more details, check out our [blog post](https://huggingface.co/blog/dpo-trl).
 
 
388
  Type in the box below and click the button to generate answers to your most pressing questions!
389
- ⚠️ **Intended Use**: this app and its [supporting model](https://huggingface.co/kashif/stack-llama-2) are provided as educational tools to explain RLHF with the TRL library; not to serve as replacement for human expertise. For more details on the model's limitations in terms of factuality and biases, see the [model card.](https://huggingface.co/kashif/stack-llama-2#intended-uses--limitations)
390
 
391
  ⚠️ **Data Collection**: by default, we are collecting the prompts entered in this app to further improve and evaluate the model. Do not share any personal or sensitive information while using the app! You can opt out of this data collection by removing the checkbox below:
392
  """
 
351
  do_save,
352
  )
353
 
354
+ title = """<h1 align="center">Chat with Gradio 💫➕</h1>"""
355
  custom_css = """
356
  #banner-image {
357
  display: block;
 
384
  with gr.Column():
385
  gr.Markdown(
386
  """![](https://huggingface.co/spaces/codeparrot/gradio-playground/resolve/main/gradio.png)
387
+ Chat-with-Gradio is a 15.5 billion parameter language model based on [BigCode's StarCoderplus model](https://huggingface.co/bigcode/starcoderplus) that has been trained on a wide variety of data sources. It includes the source code and issues on [gradio's Github repository](https://github.com/gradio-app/gradio) and data from [Hugging Face's spaces](https://huggingface.co/spaces). Its training
388
+ also involves instruction fine-tuning with a processed subset of [OpenAssistant's oasst1 dataset](https://huggingface.co/datasets/HuggingFaceH4/oasst1_en).
389
+
390
  Type in the box below and click the button to generate answers to your most pressing questions!
391
+ ⚠️ **Intended Use**: this app and its [supporting model](https://huggingface.co/bigcode/starcoderplus) are provided as tools to provide assistance when using gradio ; not to serve as replacement for human expertise. For more details on the model's limitations in terms of factuality and biases, see the [model card.](https://huggingface.co/bigcode/starcoderplus#intended-uses--limitations)
392
 
393
  ⚠️ **Data Collection**: by default, we are collecting the prompts entered in this app to further improve and evaluate the model. Do not share any personal or sensitive information while using the app! You can opt out of this data collection by removing the checkbox below:
394
  """