Instructions to use tencent/WeDLM-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/WeDLM-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="tencent/WeDLM-8B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tencent/WeDLM-8B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tencent/WeDLM-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/WeDLM-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/WeDLM-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent/WeDLM-8B-Instruct

SGLang

How to use tencent/WeDLM-8B-Instruct 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 "tencent/WeDLM-8B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/WeDLM-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "tencent/WeDLM-8B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/WeDLM-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent/WeDLM-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/tencent/WeDLM-8B-Instruct
```

hi i write a openai compatible api server for wedlm 8b

by CHONGYOEYAT - opened Dec 30, 2025

Discussion

CHONGYOEYAT

Dec 30, 2025

🚀 Just got Tencent's WeDLM running with an OpenAI-compatible API server! 🎉

Super smooth setup using FastAPI + UV package manager. Now I can easily integrate WeDLM-8B-Instruct into my projects with standard OpenAI client libraries.

📦 Quick setup:
1️⃣ Install dependencies
2️⃣ Download the model
3️⃣ Run the server
4️⃣ Start making API calls!

Already seeing great performance with flash-attention optimization. If you're working with LLMs, definitely worth checking out.

Check it out here: https://gist.github.com/cyysky/bedad2eeb7e440f5838e7cb8d2f11ca6

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