vilm/OpenOrca-Viet
Viewer • Updated • 121k • 89 • 16
How to use vilm/vietcuna-7b-v3 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="vilm/vietcuna-7b-v3") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("vilm/vietcuna-7b-v3")
model = AutoModelForCausalLM.from_pretrained("vilm/vietcuna-7b-v3")How to use vilm/vietcuna-7b-v3 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vilm/vietcuna-7b-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "vilm/vietcuna-7b-v3",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/vilm/vietcuna-7b-v3
How to use vilm/vietcuna-7b-v3 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "vilm/vietcuna-7b-v3" \
--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": "vilm/vietcuna-7b-v3",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "vilm/vietcuna-7b-v3" \
--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": "vilm/vietcuna-7b-v3",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use vilm/vietcuna-7b-v3 with Docker Model Runner:
docker model run hf.co/vilm/vietcuna-7b-v3
Vietcuna-7B v3.0
Prompt Template:
Một cuộc trò chuyện giữa một người dùng tò mò và một trợ lý trí tuệ nhân tạo. Trợ lý đưa ra các câu trả lời hữu ích, chi tiết và lịch sự cho các câu hỏi của người dùng.\n\n### Human: {human_message}\n\n### Assistant:"