can not API for leaderboard

#282
by zolutiontech - opened

Few days ago did it works. I could just write the following and get all models
client = Client("https://huggingfaceh4-open-llm-leaderboard.hf.space/")
result = client.predict()
print(result)

from gradio_client import Client

client = Client("https://huggingfaceh4-open-llm-leaderboard.hf.space/")
result = client.predict(
"null", # str in 'Model name' Textbox component
"null", # str in 'Base model (for delta or adapter weights)' Textbox component
"Howdy!", # str in 'revision' Textbox component
"['float16', 'bfloat16', '8bit (LLM.int8)', '4bit (QLoRA / FP4)', 'GPTQ']", # str (Option from: ['float16', 'bfloat16', '8bit (LLM.int8)', '4bit (QLoRA / FP4)', 'GPTQ'])
True, # bool in 'Private' Checkbox component
"['Original', 'Delta', 'Adapter']", # str (Option from: ['Original', 'Delta', 'Adapter'])
"['🟢 : pretrained', '🔶 : fine-tuned', '⭕ : instruction-tuned', '🟦 : RL-tuned']", # str (Option from: ['🟢 : pretrained', '🔶 : fine-tuned', '⭕ : instruction-tuned', '🟦 : RL-tuned'])
fn_index=5
)
print(result)

Open LLM Leaderboard org

Hi!
We upgraded Gradio to its latest version during the week, it is possible that API calls changed. I invite you to open an issue on the Gradio github directly :)

clefourrier changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment