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

Libraries

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

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

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

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

tokenizer = AutoTokenizer.from_pretrained("Salesforce/xgen-7b-8k-inst")
model = AutoModelForCausalLM.from_pretrained("Salesforce/xgen-7b-8k-inst", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

fim_tokens, what is its use?

#10

by NickyNicky - opened Jul 2, 2023

Discussion

NickyNicky

Jul 2, 2023

Hello, I hope everything goes well.

https://huggingface.co/Salesforce/xgen-7b-8k-inst/blob/main/tokenization_xgen.py

fim_tokens = [
            "<fim_prefix>",
            "<fim_middle>",
            "<fim_suffix>",
            "<fim_pad>",
            "<filename>",
            "<gh_stars>",
            "<issue_start>",
            "<issue_comment>",
            "<issue_closed>",
            "<jupyter_start>",
            "<jupyter_text>",
            "<jupyter_code>",
            "<jupyter_output>",
            "<empty_output>",
            "<commit_before>",
            "<commit_msg>",
            "<commit_after>",
            "<reponame>"
        ]

Could you explain these special tokens how they are used, thanks

rooa

Salesforce AI Research org Jul 2, 2023

The following appears in StarCoderData, the code data we used for training the model:

            "<filename>",
            "<gh_stars>",
            "<issue_start>",
            "<issue_comment>",
            "<issue_closed>",
            "<jupyter_start>",
            "<jupyter_text>",
            "<jupyter_code>",
            "<jupyter_output>",
            "<empty_output>",
            "<commit_before>",
            "<commit_msg>",
            "<commit_after>",
            "<reponame>"

Please refer to the StarCoder paper for more details. You could, for example, condition the generation using these special tokens to bias the model prediction.

The remaining (as follows) are the special tokens used by StarCoder for their FIM training, but we did not use them. You can ignore these tokens:

            "<fim_prefix>",
            "<fim_middle>",
            "<fim_suffix>",
            "<fim_pad>",

rooa changed discussion status to closed Jul 2, 2023

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