How to use from
SGLangUse 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 "qilowoq/Vikhr-Nemo-12B-Instruct-R-21-09-24-4Bit-GPTQ" \
--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": "qilowoq/Vikhr-Nemo-12B-Instruct-R-21-09-24-4Bit-GPTQ",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'Quick Links
Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24-4Bit-GPTQ
- Original Model: Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
Quantization
- This model was quantized with the Auto-GPTQ library and dataset containing english and russian wikipedia articles. It has lower perplexity on russian data then other GPTQ models.
- Downloads last month
- 34
Model tree for qilowoq/Vikhr-Nemo-12B-Instruct-R-21-09-24-4Bit-GPTQ
Base model
mistralai/Mistral-Nemo-Base-2407 Finetuned
mistralai/Mistral-Nemo-Instruct-2407
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "qilowoq/Vikhr-Nemo-12B-Instruct-R-21-09-24-4Bit-GPTQ" \ --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": "qilowoq/Vikhr-Nemo-12B-Instruct-R-21-09-24-4Bit-GPTQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'