zstanjj/SlimPLM-Query-Rewriting

SlimPLM

📝 Paper • 🤗 Hugging Face • 🧩 Github

🌹 If you use this model, please star our GitHub repository to support us. Your star means a lot!

✨ Latest News

• [1/25/2024]: Retrieval Necessity Judgment Model released in Hugging Face.
• [2/20/2024]: Query Rewriting Model released in Hugging Face.
• [5/19/2024]: Our new work, Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs, has been accepted by ACL 2024 main conference.

🎬 Get Started

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# construct prompt
question = "Who voices Darth Vader in Star Wars Episodes III-VI, IX Rogue One, and Rebels?"
heuristic_answer = "The voice of Darth Vader in Star Wars is provided by British actor James Earl Jones. He first voiced the character in the 1977 film \"Star Wars: Episode IV - A New Hope\", and his performance has been used in all subsequent Star Wars films, including the prequels and sequels."
prompt = (f"<s>[INST] <<SYS>>\nYou are a helpful assistant. Your task is to parse user input into"
          f" structured formats according to the coarse answer. Current datatime is 2023-12-20 9:47:28"
          f" <</SYS>>\n Course answer: (({heuristic_answer}))\nQuestion: (({question})) [/INST]")

# alternatively you can input question only
# prompt = (f"<s>[INST] <<SYS>>\nYou are a helpful assistant. Your task is to parse user input into"
#           f" structured formats. Current datatime is 2023-12-20 9:47:28"
#           f" <</SYS>>\n{question} [/INST]")

params_query_rewrite = {"repetition_penalty": 1.05, "temperature": 0.01, "top_k": 1, "top_p": 0.85,
                        "max_new_tokens": 512, "do_sample": False, "seed": 2023}

# deploy model
model = AutoModelForCausalLM.from_pretrained("zstanjj/SlimPLM-Query-Rewriting").eval()
if torch.cuda.is_available():
    model.cuda()
tokenizer = AutoTokenizer.from_pretrained("zstanjj/SlimPLM-Query-Rewriting")

# run inference 
input_ids = tokenizer.encode(prompt.format(question=question, answer=heuristic_answer), return_tensors="pt")
len_input_ids = len(input_ids[0])
if torch.cuda.is_available():
    input_ids = input_ids.cuda()
outputs = model.generate(input_ids)
res = tokenizer.decode(outputs[0][len_input_ids:], skip_special_tokens=True)
print(res)

✏️ Citation

@inproceedings{Tan2024SmallMB,
  title={Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs},
  author={Jiejun Tan and Zhicheng Dou and Yutao Zhu and Peidong Guo and Kun Fang and Ji-Rong Wen},
  year={2024},
  url={https://arxiv.org/abs/2402.12052}
}