Instructions to use zorazrw/filco-llama2-dialog with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zorazrw/filco-llama2-dialog with Transformers:

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

pipe = pipeline("text-generation", model="zorazrw/filco-llama2-dialog")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zorazrw/filco-llama2-dialog")
model = AutoModelForCausalLM.from_pretrained("zorazrw/filco-llama2-dialog", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zorazrw/filco-llama2-dialog with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zorazrw/filco-llama2-dialog"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zorazrw/filco-llama2-dialog",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zorazrw/filco-llama2-dialog

SGLang

How to use zorazrw/filco-llama2-dialog 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 "zorazrw/filco-llama2-dialog" \
    --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": "zorazrw/filco-llama2-dialog",
		"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 "zorazrw/filco-llama2-dialog" \
        --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": "zorazrw/filco-llama2-dialog",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zorazrw/filco-llama2-dialog with Docker Model Runner:
```
docker model run hf.co/zorazrw/filco-llama2-dialog
```

This is a FilCo context filtering model for knowledge-grounded dialog generation tasks, particularly in the open domain. Specifically, this is a meta-llama/Llama-2-7b trained using LoRA for 3 epochs on the Wizard of Wikipedia (WoW) training set.

It is intended to be used in FilCo: https://github.com/zorazrw/filco, but can be further applied in similar scenarios.

Citation

if you use this model for research, please cite:

@article{wang2023learning,
  title={Learning to Filter Context for Retrieval-Augmented Generation},
  author={Zhiruo Wang, Jun Araki, Zhengbao Jiang, Md Rizwan Parvez, Graham Neubig},
  journal={arXiv preprint arXiv:2311.08377},
  year={2023}
}

Downloads last month: 15

Paper for zorazrw/filco-llama2-dialog

Learning to Filter Context for Retrieval-Augmented Generation

Paper • 2311.08377 • Published Nov 14, 2023