Instructions to use GitBag/Reviewer2_Mp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GitBag/Reviewer2_Mp with Transformers:

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

pipe = pipeline("text-generation", model="GitBag/Reviewer2_Mp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GitBag/Reviewer2_Mp")
model = AutoModelForCausalLM.from_pretrained("GitBag/Reviewer2_Mp", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GitBag/Reviewer2_Mp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GitBag/Reviewer2_Mp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GitBag/Reviewer2_Mp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GitBag/Reviewer2_Mp

SGLang

How to use GitBag/Reviewer2_Mp 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 "GitBag/Reviewer2_Mp" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GitBag/Reviewer2_Mp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "GitBag/Reviewer2_Mp" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GitBag/Reviewer2_Mp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GitBag/Reviewer2_Mp with Docker Model Runner:
```
docker model run hf.co/GitBag/Reviewer2_Mp
```

GitBag commited on Feb 25, 2024

Commit

9eed3b7

verified ·

1 Parent(s): 7460eea

Create README.md

Browse files

Files changed (1) hide show

README.md +30 -0

README.md CHANGED Viewed

	@@ -0,0 +1,30 @@

+---
+license: apache-2.0
+datasets:
+- GitBag/Reviewer2_PGE_cleaned
+language:
+- en
+metrics:
+- bleu
+- rouge
+- bertscore
+---
+# Prompt Generation Model for [Reviewer2](https://arxiv.org/abs/2402.10886)
+This is the prompt generation model (Mp) for our Reviewer2 pipeline. A demo of the model is provided in this [repo](https://github.com/ZhaolinGao/Reviewer2/tree/main).
+## Citation
+If you find this model useful in your research, please cite the following paper:
+```
+@misc{gao2024reviewer2,
+      title={Reviewer2: Optimizing Review Generation Through Prompt Generation},
+      author={Zhaolin Gao and Kianté Brantley and Thorsten Joachims},
+      year={2024},
+      eprint={2402.10886},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```