Instructions to use Salesforce/xgen-7b-4k-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/xgen-7b-4k-base with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/xgen-7b-4k-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/xgen-7b-4k-base")
model = AutoModelForCausalLM.from_pretrained("Salesforce/xgen-7b-4k-base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/xgen-7b-4k-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-4k-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-4k-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/xgen-7b-4k-base

SGLang

How to use Salesforce/xgen-7b-4k-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-4k-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-4k-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-4k-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-4k-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/xgen-7b-4k-base with Docker Model Runner:
```
docker model run hf.co/Salesforce/xgen-7b-4k-base
```

GGML format

by slavag - opened Jun 29, 2023

Discussion

slavag

Jun 29, 2023

Hi,
How can I convert this model to GGML ?

Thanks

srinivasbilla

Jul 3, 2023

•

edited Jul 3, 2023

@TheBloke As far as I can tell this is an open reproduction of LLaMA. Could you convert it to GGML/GPTQ pls? Would be great to benchmark this. And also the other two released by salesforce

TheBloke

Jul 3, 2023

I've been looking into this and would love to do it. The problem is while it uses Llama for the weights, it uses a custom tokenizer (tiktoken). So GGML support won't be possible until they add specific support for that.

Otherwise I believe it will just produce gibberish, because the text you enter and the model outputs will be converted to/from the wrong token ids.

I'll give it a test later today but I'm pretty sure it can't work atm.

srinivasbilla

Jul 3, 2023

Ah I see makes sense. Thanks for the rapid reply.

appvoid

Jul 7, 2023

I see GPT-2 name in the tokenizer, maybe the trick is using existing GPT-2 GGML tokenizer example?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment