Instructions to use HillZhang/untruthful_llama2_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HillZhang/untruthful_llama2_7b with Transformers:

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

pipe = pipeline("text-generation", model="HillZhang/untruthful_llama2_7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HillZhang/untruthful_llama2_7b")
model = AutoModelForCausalLM.from_pretrained("HillZhang/untruthful_llama2_7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HillZhang/untruthful_llama2_7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HillZhang/untruthful_llama2_7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HillZhang/untruthful_llama2_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HillZhang/untruthful_llama2_7b

SGLang

How to use HillZhang/untruthful_llama2_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 "HillZhang/untruthful_llama2_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": "HillZhang/untruthful_llama2_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 "HillZhang/untruthful_llama2_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": "HillZhang/untruthful_llama2_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HillZhang/untruthful_llama2_7b with Docker Model Runner:
```
docker model run hf.co/HillZhang/untruthful_llama2_7b
```

Untruthful-Llama2-7B

We induce hallucinations from the original Llama2-7B by finetuning it on selected samples from HaluEval. We then use it in our ICD method for improve factuality of LLMs and evaluate the effectiveness on TruthfulQA. More details are provided in our Github and Paper.

Downloads last month: 14

HillZhang
/

untruthful_llama2_7b

Untruthful-Llama2-7B

Dataset used to train HillZhang/untruthful_llama2_7b