Tweak preamble text

#1
by lewtun HF staff - opened
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -202,7 +202,7 @@ with block:
202
  with gr.Row():
203
  gr.Markdown(f"""
204
  # πŸ€— Open LLM Leaderboard
205
- <font size="4">With the plethora of chatbot LLMs being released week upon week, often with grandiose claims of their performance, it can be hard to filter out the genuine progress that is being made by the open-source community and which chatbot is the current state of the art. The πŸ€— Open Chatbot Leaderboard aims to track, rank and evaluate chatbot models as they are released. We evaluate models of 4 key benchmarks from the <a href="https://github.com/EleutherAI/lm-evaluation-harness" target="_blank"> Eleuther AI Language Model Evaluation Harness </a>, a unified framework to test generative language models on a large number of different evaluation tasks. A key advantage of this leaderboard is that anyone from the community can submit a model for automated evaluation on the πŸ€— research cluster. As long as it is Transformers model with weights on the πŸ€— hub. We also support delta-weights for non-commercial licensed models, such as llama.
206
 
207
  Evaluation is performed against 4 popular benchmarks:
208
  - <a href="https://arxiv.org/abs/1803.05457" target="_blank"> AI2 Reasoning Challenge </a> (25-shot) - a set of grade-school science questions.
 
202
  with gr.Row():
203
  gr.Markdown(f"""
204
  # πŸ€— Open LLM Leaderboard
205
+ <font size="4">With the plethora of large language models (LLMs) and chatbots being released week upon week, often with grandiose claims of their performance, it can be hard to filter out the genuine progress that is being made by the open-source community and which model is the current state of the art. The πŸ€— Open LLM Leaderboard aims to track, rank and evaluate LLMs and chatbots as they are released. We evaluate models on 4 key benchmarks from the <a href="https://github.com/EleutherAI/lm-evaluation-harness" target="_blank"> Eleuther AI Language Model Evaluation Harness </a>, a unified framework to test generative language models on a large number of different evaluation tasks. A key advantage of this leaderboard is that anyone from the community can submit a model for automated evaluation on the πŸ€— GPU cluster, as long as it is a πŸ€— Transformers model with weights on the Hub. We also support evaluation of models with delta-weights for non-commercial licensed models, such as LLaMa.
206
 
207
  Evaluation is performed against 4 popular benchmarks:
208
  - <a href="https://arxiv.org/abs/1803.05457" target="_blank"> AI2 Reasoning Challenge </a> (25-shot) - a set of grade-school science questions.