Instructions to use RedHatAI/starcoder2-7b-quantized.w8a8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/starcoder2-7b-quantized.w8a8 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/starcoder2-7b-quantized.w8a8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/starcoder2-7b-quantized.w8a8")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/starcoder2-7b-quantized.w8a8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/starcoder2-7b-quantized.w8a8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/starcoder2-7b-quantized.w8a8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/starcoder2-7b-quantized.w8a8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/starcoder2-7b-quantized.w8a8

SGLang

How to use RedHatAI/starcoder2-7b-quantized.w8a8 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 "RedHatAI/starcoder2-7b-quantized.w8a8" \
    --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": "RedHatAI/starcoder2-7b-quantized.w8a8",
		"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 "RedHatAI/starcoder2-7b-quantized.w8a8" \
        --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": "RedHatAI/starcoder2-7b-quantized.w8a8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/starcoder2-7b-quantized.w8a8 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/starcoder2-7b-quantized.w8a8
```

question about deploying the model using containers

by rthenamvar - opened Feb 14, 2025

Discussion

rthenamvar

Feb 14, 2025

Hi, I hope everything is great for you. I'm trying to deploy this model using Docker containers. The model is deployed successfully and generates prompts, but is really slow compared to other models currently deployed (Qwen2.5-7B-Instruct-GPTQ-Int4). So I'm guessing that there may be something wrong with my config which is here:

--model neuralmagic/starcoder2-7b-quantized.w8a8
--disable-log-requests
--enable-prefix-caching
--use-v2-block-manager
--max_num_batched_tokens 32000
--disable-sliding-window
--block-size 32
--max-num-seqs 600"

I would appreciate any kind of help

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