Instructions to use Salesforce/xgen-7b-8k-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/xgen-7b-8k-base with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/xgen-7b-8k-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/xgen-7b-8k-base")
model = AutoModelForCausalLM.from_pretrained("Salesforce/xgen-7b-8k-base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/xgen-7b-8k-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/xgen-7b-8k-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/xgen-7b-8k-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/xgen-7b-8k-base

SGLang

How to use Salesforce/xgen-7b-8k-base 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 "Salesforce/xgen-7b-8k-base" \
    --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": "Salesforce/xgen-7b-8k-base",
		"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 "Salesforce/xgen-7b-8k-base" \
        --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": "Salesforce/xgen-7b-8k-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/xgen-7b-8k-base with Docker Model Runner:
```
docker model run hf.co/Salesforce/xgen-7b-8k-base
```

enijkamp commited on Jun 30, 2023

Commit

f763572

1 Parent(s): b8cb7a8

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ Official research release for the family of **XGen** models (`7B`) by Salesforce
 *Title*: [Long Sequence Modeling with XGen: A 7B LLM Trained on 8K Input Sequence Length](https://blog.salesforceairesearch.com/xgen/)
-*Authors*: [Erik Nijkamp](https://eriknijkamp.com)\*, Tian Xie\*, [Hiroaki Hayashi](https://hiroakih.me/)\*, [Bo Pang](https://scholar.google.com/citations?user=s9fNEVEAAAAJ&hl=en)\*, Congying Xia\*, Chen Xing, Rui Meng, Wojciech Kryscinski, Lifu Tu, Meghana Bhat, Semih Yavuz, Jesse Vig, Lidiya Murakhovs'ka, [Chien-Sheng Wu](https://jasonwu0731.github.io/), [Yingbo Zhou](https://scholar.google.com/citations?user=H_6RQ7oAAAAJ&hl=en), [Shafiq Rayhan Joty](https://raihanjoty.github.io/), [Caiming Xiong](http://cmxiong.com/), Silvio Savarese.
 (* indicates equal contribution)
@@ -55,7 +55,7 @@ print(tokenizer.decode(sample[0]))
 ```bibtex
 @misc{XGen,
   title={Long Sequence Modeling with XGen: A 7B LLM Trained on 8K Input Sequence Length},
-  author={Erik Nijkamp, Tian Xie, Hiroaki Hayashi, Bo Pang, Congying Xia, Chen Xing, Rui Meng, Wojciech Kryscinski, Lifu Tu, Meghana Bhat, Semih Yavuz, Jesse Vig, Lidiya Murakhovs'ka, Chien-Sheng Wu, Yingbo Zhou, Shafiq Rayhan Joty, Caiming Xiong, Silvio Savarese},
   howpublished={Salesforce AI Research Blog},
   year={2023},
   url={https://blog.salesforceairesearch.com/xgen}

 *Title*: [Long Sequence Modeling with XGen: A 7B LLM Trained on 8K Input Sequence Length](https://blog.salesforceairesearch.com/xgen/)
+*Authors*: [Erik Nijkamp](https://eriknijkamp.com)\*, Tian Xie\*, [Hiroaki Hayashi](https://hiroakih.me/)\*, [Bo Pang](https://scholar.google.com/citations?user=s9fNEVEAAAAJ&hl=en)\*, Congying Xia\*, Chen Xing, Jesse Vig, Semih Yavuz, Philippe Laban, Ben Krause, Senthil Purushwalkam, Tong Niu, Wojciech Kryscinski, Lidiya Murakhovs'ka, Prafulla Kumar Choubey, Alex Fabbri, Ye Liu, Rui Meng, Lifu Tu, Meghana Bhat, [Chien-Sheng Wu](https://jasonwu0731.github.io/), Silvio Savarese, [Yingbo Zhou](https://scholar.google.com/citations?user=H_6RQ7oAAAAJ&hl=en), [Shafiq Rayhan Joty](https://raihanjoty.github.io/), [Caiming Xiong](http://cmxiong.com/).
 (* indicates equal contribution)
 ```bibtex
 @misc{XGen,
   title={Long Sequence Modeling with XGen: A 7B LLM Trained on 8K Input Sequence Length},
+  author={Erik Nijkamp, Tian Xie, Hiroaki Hayashi, Bo Pang, Congying Xia, Chen Xing, Jesse Vig, Semih Yavuz, Philippe Laban, Ben Krause, Senthil Purushwalkam, Tong Niu, Wojciech Kryscinski, Lidiya Murakhovs'ka, Prafulla Kumar Choubey, Alex Fabbri, Ye Liu, Rui Meng, Lifu Tu, Meghana Bhat, Chien-Sheng Wu, Silvio Savarese, Yingbo Zhou, Shafiq Rayhan Joty, Caiming Xiong},
   howpublished={Salesforce AI Research Blog},
   year={2023},
   url={https://blog.salesforceairesearch.com/xgen}