Instructions to use lzw1008/ConspEmoLLM-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lzw1008/ConspEmoLLM-7b with Transformers:

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

pipe = pipeline("text-generation", model="lzw1008/ConspEmoLLM-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lzw1008/ConspEmoLLM-7b")
model = AutoModelForCausalLM.from_pretrained("lzw1008/ConspEmoLLM-7b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lzw1008/ConspEmoLLM-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lzw1008/ConspEmoLLM-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lzw1008/ConspEmoLLM-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lzw1008/ConspEmoLLM-7b

SGLang

How to use lzw1008/ConspEmoLLM-7b 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 "lzw1008/ConspEmoLLM-7b" \
    --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": "lzw1008/ConspEmoLLM-7b",
		"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 "lzw1008/ConspEmoLLM-7b" \
        --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": "lzw1008/ConspEmoLLM-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lzw1008/ConspEmoLLM-7b with Docker Model Runner:
```
docker model run hf.co/lzw1008/ConspEmoLLM-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Github LINK

Citation

If you use the ConspEmoLLM or ConspLLM in your work, please cite our paper:

@article{liu2024conspemollm,
  title={ConspEmoLLM: Conspiracy Theory Detection Using an Emotion-Based Large Language Model},
  author={Liu, Zhiwei and Liu, Boyang and Thompson, Paul and Yang, Kailai and Jain, Raghav and Ananiadou, Sophia},
  journal={arXiv preprint arXiv:2403.06765},
  year={2024}
}

Downloads last month: 36

Safetensors

Model size

7B params

Tensor type

F16

Model tree for lzw1008/ConspEmoLLM-7b

Quantizations

2 models

Space using lzw1008/ConspEmoLLM-7b 1

Paper for lzw1008/ConspEmoLLM-7b

ConspEmoLLM: Conspiracy Theory Detection Using an Emotion-Based Large Language Model

Paper • 2403.06765 • Published Mar 11, 2024 • 1