yahma/alpaca-cleaned
Viewer • Updated • 51.8k • 33.5k • 823
How to use ayuan0324/alpaca-loraa with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="ayuan0324/alpaca-loraa") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("ayuan0324/alpaca-loraa")
model = AutoModelForCausalLM.from_pretrained("ayuan0324/alpaca-loraa")How to use ayuan0324/alpaca-loraa with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ayuan0324/alpaca-loraa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "ayuan0324/alpaca-loraa",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/ayuan0324/alpaca-loraa
How to use ayuan0324/alpaca-loraa with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "ayuan0324/alpaca-loraa" \
--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": "ayuan0324/alpaca-loraa",
"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 "ayuan0324/alpaca-loraa" \
--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": "ayuan0324/alpaca-loraa",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use ayuan0324/alpaca-loraa with Docker Model Runner:
docker model run hf.co/ayuan0324/alpaca-loraa
This repository contains a LLaMA-7B fine-tuned model on the Standford Alpaca cleaned version dataset and ocean_only data