Tiiny/LONGCOT-Refine-500K
Viewer • Updated • 522k • 945 • 51
How to use adriabama06/SmallThinker-3B-Preview-AWQ with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adriabama06/SmallThinker-3B-Preview-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "adriabama06/SmallThinker-3B-Preview-AWQ",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/adriabama06/SmallThinker-3B-Preview-AWQ
How to use adriabama06/SmallThinker-3B-Preview-AWQ with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "adriabama06/SmallThinker-3B-Preview-AWQ" \
--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": "adriabama06/SmallThinker-3B-Preview-AWQ",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'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 "adriabama06/SmallThinker-3B-Preview-AWQ" \
--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": "adriabama06/SmallThinker-3B-Preview-AWQ",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'How to use adriabama06/SmallThinker-3B-Preview-AWQ with Docker Model Runner:
docker model run hf.co/adriabama06/SmallThinker-3B-Preview-AWQ
AWQ 4 bit, 128 groupsize of PowerInfer/SmallThinker-3B-Preview
Warning: This model seems to not work, not at least in my computer with vLLM
Base model
Qwen/Qwen2.5-3B