garage-bAInd/Open-Platypus
Viewer • Updated • 24.9k • 9.2k • 417
How to use Weyaxi/Nova-13B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Weyaxi/Nova-13B") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Weyaxi/Nova-13B")
model = AutoModelForCausalLM.from_pretrained("Weyaxi/Nova-13B")How to use Weyaxi/Nova-13B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Weyaxi/Nova-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Weyaxi/Nova-13B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Weyaxi/Nova-13B
How to use Weyaxi/Nova-13B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Weyaxi/Nova-13B" \
--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": "Weyaxi/Nova-13B",
"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 "Weyaxi/Nova-13B" \
--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": "Weyaxi/Nova-13B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Weyaxi/Nova-13B with Docker Model Runner:
docker model run hf.co/Weyaxi/Nova-13B
Original weights of Nova-13B. Finetuned from AIDC-ai-business/Luban-13B.
You can access adapter weights from here:
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 49.64 |
| ARC (25-shot) | 62.71 |
| HellaSwag (10-shot) | 82.57 |
| MMLU (5-shot) | 57.98 |
| TruthfulQA (0-shot) | 51.34 |
| Winogrande (5-shot) | 77.27 |
| GSM8K (5-shot) | 6.75 |
| DROP (3-shot) | 8.84 |