Instructions to use zstanjj/SlimPLM-Query-Rewriting with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zstanjj/SlimPLM-Query-Rewriting with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="zstanjj/SlimPLM-Query-Rewriting")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zstanjj/SlimPLM-Query-Rewriting")
model = AutoModelForCausalLM.from_pretrained("zstanjj/SlimPLM-Query-Rewriting", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zstanjj/SlimPLM-Query-Rewriting with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zstanjj/SlimPLM-Query-Rewriting"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zstanjj/SlimPLM-Query-Rewriting",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zstanjj/SlimPLM-Query-Rewriting

SGLang

How to use zstanjj/SlimPLM-Query-Rewriting with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "zstanjj/SlimPLM-Query-Rewriting" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zstanjj/SlimPLM-Query-Rewriting",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "zstanjj/SlimPLM-Query-Rewriting" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zstanjj/SlimPLM-Query-Rewriting",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zstanjj/SlimPLM-Query-Rewriting with Docker Model Runner:
```
docker model run hf.co/zstanjj/SlimPLM-Query-Rewriting
```

SlimPLM-Query-Rewriting / README.md

zstanjj

Update README.md

cea2117 verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

3.31 kB

metadata

license: llama2

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}
}