Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -118,13 +118,13 @@ with gr.Blocks() as demo:
|
|
118 |
gr.Image("better_banner.jpeg", elem_id="banner-image", show_label=False)
|
119 |
with gr.Column():
|
120 |
gr.Markdown(
|
121 |
-
"""# Falcon-180B
|
122 |
|
123 |
**Chat with [Falcon-180B-Chat](https://huggingface.co/tiiuae/falcon-180b-chat), brainstorm ideas, discuss your holiday plans, and more!**
|
124 |
|
125 |
β¨ This demo is powered by [Falcon-180B](https://huggingface.co/tiiuae/falcon-180B) and finetuned on a mixture of [Ultrachat](https://huggingface.co/datasets/stingning/ultrachat), [Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus) and [Airoboros](https://huggingface.co/datasets/jondurbin/airoboros-2.1). [Falcon-180B](https://huggingface.co/tiiuae/falcon-180b) 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 3.5 trillion tokens (including [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)) and available under the Apache 2.0 license. It currently holds the π₯ 1st place on the [π€ Open LLM leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for a pretrained model.
|
126 |
|
127 |
-
π§ͺ This is only a **first experimental preview**: we intend to provide increasingly capable versions of Falcon
|
128 |
|
129 |
π **Learn more about Falcon LLM:** [falconllm.tii.ae](https://falconllm.tii.ae/)
|
130 |
|
|
|
118 |
gr.Image("better_banner.jpeg", elem_id="banner-image", show_label=False)
|
119 |
with gr.Column():
|
120 |
gr.Markdown(
|
121 |
+
"""# Falcon-180B Demo
|
122 |
|
123 |
**Chat with [Falcon-180B-Chat](https://huggingface.co/tiiuae/falcon-180b-chat), brainstorm ideas, discuss your holiday plans, and more!**
|
124 |
|
125 |
β¨ This demo is powered by [Falcon-180B](https://huggingface.co/tiiuae/falcon-180B) and finetuned on a mixture of [Ultrachat](https://huggingface.co/datasets/stingning/ultrachat), [Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus) and [Airoboros](https://huggingface.co/datasets/jondurbin/airoboros-2.1). [Falcon-180B](https://huggingface.co/tiiuae/falcon-180b) 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 3.5 trillion tokens (including [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)) and available under the Apache 2.0 license. It currently holds the π₯ 1st place on the [π€ Open LLM leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for a pretrained model.
|
126 |
|
127 |
+
π§ͺ This is only a **first experimental preview**: we intend to provide increasingly capable versions of Falcon in the future, based on improved datasets and RLHF/RLAIF.
|
128 |
|
129 |
π **Learn more about Falcon LLM:** [falconllm.tii.ae](https://falconllm.tii.ae/)
|
130 |
|