tatsu-lab/alpaca
Viewer • Updated • 52k • 97.4k • 959
How to use hiyouga/Yi-Agent-6B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="hiyouga/Yi-Agent-6B") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("hiyouga/Yi-Agent-6B")
model = AutoModelForCausalLM.from_pretrained("hiyouga/Yi-Agent-6B")How to use hiyouga/Yi-Agent-6B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hiyouga/Yi-Agent-6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "hiyouga/Yi-Agent-6B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/hiyouga/Yi-Agent-6B
How to use hiyouga/Yi-Agent-6B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "hiyouga/Yi-Agent-6B" \
--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": "hiyouga/Yi-Agent-6B",
"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 "hiyouga/Yi-Agent-6B" \
--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": "hiyouga/Yi-Agent-6B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use hiyouga/Yi-Agent-6B with Docker Model Runner:
docker model run hf.co/hiyouga/Yi-Agent-6B
A bilingual model with function calling abilities.
Usage:
Launch a RESTFul API by using the script in LLaMA-Factory
python src/api_demo.py --template default --model_name_or_path hiyouga/Yi-Agent-6B
Test with:
https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/test_toolcall.py
You can reproduce our results with the step-by-step (Chinese) guide: