import vllm
import torch
import gradio
import huggingface_hub
import os
huggingface_hub.login(token=os.environ["HF_TOKEN"])
# Fava prompt
INPUT = "Read the following references:\n{evidence}\nPlease identify all the errors in the following text using the information in the references provided and suggest edits if necessary:\n[Text] {output}\n[Edited] "
model = vllm.LLM(model="uw-llm-factuality/FAVA")
def result(passage, reference):
prompt = [INPUT.format_map({"evidence":reference, "output":passage})]
print(prompt)
print("\n")
sampling_params = vllm.SamplingParams(
temperature=0,
top_p=1.0,
max_tokens=500,
)
outputs = model.generate(prompt, sampling_params)
outputs = [it.outputs[0].text for it in outputs]
output = outputs[0].replace("", " ")
output = output.replace("", " ")
output = output.replace("