jaumaras commited on
Commit
8b62e72
·
1 Parent(s): 25a489b

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +9 -11
app.py CHANGED
@@ -1,17 +1,15 @@
1
  import gradio as gr
2
 
3
- this_Markdown=(
4
- """**Chat with [Falcon-40B-Instruct](https://huggingface.co/tiiuae/falcon-40b-instruct), brainstorm ideas, discuss your holiday plans, and more!**
5
- ✨ This demo is powered by [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b), finetuned on the [Baize](https://github.com/project-baize/baize-chatbot) dataset, and running with [Text Generation Inference](https://github.com/huggingface/text-generation-inference). [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) is a state-of-the-art large language model built by the [Technology Innovation Institute](https://www.tii.ae) in Abu Dhabi. It is trained on 1 trillion tokens (including [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)) and available under the Apache 2.0 license. It currently holds the 🥇 1st place on the [🤗 Open LLM leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). This demo is made available by the [HuggingFace H4 team](https://huggingface.co/HuggingFaceH4).
6
- 🧪 This is only a **first experimental preview**: the [H4 team](https://huggingface.co/HuggingFaceH4) intends to provide increasingly capable versions of Falcon Chat in the future, based on improved datasets and RLHF/RLAIF.
7
- 👀 **Learn more about Falcon LLM:** [falconllm.tii.ae](https://falconllm.tii.ae/)
8
- ➡️️ **Intended Use**: this demo is intended to showcase an early finetuning of [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b), to illustrate the impact (and limitations) of finetuning on a dataset of conversations and instructions. We encourage the community to further build upon the base model, and to create even better instruct/chat versions!
9
- ⚠️ **Limitations**: the model can and will produce factually incorrect information, hallucinating facts and actions. As it has not undergone any advanced tuning/alignment, it can produce problematic outputs, especially if prompted to do so. Finally, this demo is limited to a session length of about 1,000 words.
10
-
11
  Give me something to say!
12
  """)
 
 
 
 
 
13
 
14
- print(this_Markdown)
15
 
16
  tts_examples = [
17
  "I love learning machine learning",
@@ -22,14 +20,14 @@ tts_demo = gr.load(
22
  "huggingface/facebook/fastspeech2-en-ljspeech",
23
  title=None,
24
  examples=tts_examples,
25
- description=this_Markdown,
26
  )
27
 
28
  stt_demo = gr.load(
29
  "huggingface/facebook/wav2vec2-base-960h",
30
  title=None,
31
  inputs="mic",
32
- description="Let me try to guess what you're saying!",
33
  )
34
  gr.api_name="additionss"
35
  demo = gr.TabbedInterface([tts_demo, stt_demo], ["Text-to-speech", "Speech-to-text"],css=".gradio-container {background-color: black}")
 
1
  import gradio as gr
2
 
3
+ this_Markdown1=(
4
+ """**
 
 
 
 
 
 
5
  Give me something to say!
6
  """)
7
+ this_Markdown2=(
8
+ """**
9
+ say something and i will write it!
10
+ """)
11
+
12
 
 
13
 
14
  tts_examples = [
15
  "I love learning machine learning",
 
20
  "huggingface/facebook/fastspeech2-en-ljspeech",
21
  title=None,
22
  examples=tts_examples,
23
+ description=this_Markdown1,
24
  )
25
 
26
  stt_demo = gr.load(
27
  "huggingface/facebook/wav2vec2-base-960h",
28
  title=None,
29
  inputs="mic",
30
+ description=this_Markdown2,
31
  )
32
  gr.api_name="additionss"
33
  demo = gr.TabbedInterface([tts_demo, stt_demo], ["Text-to-speech", "Speech-to-text"],css=".gradio-container {background-color: black}")