Instructions to use selfrag/selfrag_llama2_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use selfrag/selfrag_llama2_7b with Transformers:

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

pipe = pipeline("text-generation", model="selfrag/selfrag_llama2_7b")

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

tokenizer = AutoTokenizer.from_pretrained("selfrag/selfrag_llama2_7b")
model = AutoModelForCausalLM.from_pretrained("selfrag/selfrag_llama2_7b", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use selfrag/selfrag_llama2_7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "selfrag/selfrag_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": "selfrag/selfrag_llama2_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/selfrag/selfrag_llama2_7b

SGLang

How to use selfrag/selfrag_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 "selfrag/selfrag_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": "selfrag/selfrag_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 "selfrag/selfrag_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": "selfrag/selfrag_llama2_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use selfrag/selfrag_llama2_7b with Docker Model Runner:
```
docker model run hf.co/selfrag/selfrag_llama2_7b
```

selfrag_llama2_7b

Commit History

Apr 7, 2024

21:37
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
59021db

Jan 22, 2024

04:06
update hyperlink for requirements.txt (#4)⁠

akariasai +1: herMaster

Verified signature
1902613

Oct 22, 2023

17:47
Fix the link of requirements.txt (#1)⁠

akariasai +1: Sefika

3ffae2b
17:47
update the paper link (#2)⁠

akariasai +1: Sefika

1997934

Oct 19, 2023

08:10
Update README.md

akariasai

f05576d
08:08
Update README.md

akariasai

125a51f

Oct 18, 2023

21:03
Update README.md

akariasai

a2d59cf
18:26
Create README.md

akariasai

69c96f1
04:55
Checkpoint first release.

yizhongw

7f25cee
00:12
initial commit

Akari Asai

bf32c11

Commit History

Apr 7, 2024

Adding `safetensors` variant of this model⁠

Jan 22, 2024

update hyperlink for requirements.txt (#4)⁠

Oct 22, 2023

Fix the link of requirements.txt (#1)⁠

update the paper link (#2)⁠

Oct 19, 2023

Update README.md

Update README.md

Oct 18, 2023

Update README.md

Create README.md

Checkpoint first release.

initial commit