Instructions to use CommunityLM/republican-twitter-gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CommunityLM/republican-twitter-gpt2 with Transformers:

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

pipe = pipeline("text-generation", model="CommunityLM/republican-twitter-gpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CommunityLM/republican-twitter-gpt2")
model = AutoModelForCausalLM.from_pretrained("CommunityLM/republican-twitter-gpt2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CommunityLM/republican-twitter-gpt2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CommunityLM/republican-twitter-gpt2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CommunityLM/republican-twitter-gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CommunityLM/republican-twitter-gpt2

SGLang

How to use CommunityLM/republican-twitter-gpt2 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 "CommunityLM/republican-twitter-gpt2" \
    --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": "CommunityLM/republican-twitter-gpt2",
		"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 "CommunityLM/republican-twitter-gpt2" \
        --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": "CommunityLM/republican-twitter-gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CommunityLM/republican-twitter-gpt2 with Docker Model Runner:
```
docker model run hf.co/CommunityLM/republican-twitter-gpt2
```

Model Specification

This is the Republican community GPT-2 language model, fine-tuned on 4.7M (~100M tokens) tweets of Republican Twitter users between 2019-01-01 and 2020-04-10.
For more details about the CommunityLM project, please refer to this our paper and github page.
In the paper, it is referred as the Fine-tuned CommunityLM for the Republican Twitter community.

How to use the model

PRE-PROCESSING: when you apply the model on tweets, please make sure that tweets are preprocessed by the TweetTokenizer to get the best performance.

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CommunityLM/republican-twitter-gpt2")

model = AutoModelForCausalLM.from_pretrained("CommunityLM/republican-twitter-gpt2")

References

If you use this repository in your research, please kindly cite our paper:

@inproceedings{jiang-etal-2022-communitylm,
    title = "CommunityLM: Probing Partisan Worldviews from Language Models",
     author = {Jiang, Hang and Beeferman, Doug and Roy, Brandon and Roy, Deb},
    booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
    year = "2022",
    publisher = "International Committee on Computational Linguistics",
}

Downloads last month: 1,029

Paper for CommunityLM/republican-twitter-gpt2

CommunityLM: Probing Partisan Worldviews from Language Models

Paper • 2209.07065 • Published Sep 15, 2022