beomi/KoAlpaca-v1.1a
Viewer β’ Updated β’ 21.2k β’ 987 β’ 63
How to use blueapple8259/ANHSY_0.1 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="blueapple8259/ANHSY_0.1") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("blueapple8259/ANHSY_0.1")
model = AutoModelForCausalLM.from_pretrained("blueapple8259/ANHSY_0.1", device_map="auto")How to use blueapple8259/ANHSY_0.1 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blueapple8259/ANHSY_0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "blueapple8259/ANHSY_0.1",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/blueapple8259/ANHSY_0.1
How to use blueapple8259/ANHSY_0.1 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "blueapple8259/ANHSY_0.1" \
--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": "blueapple8259/ANHSY_0.1",
"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 "blueapple8259/ANHSY_0.1" \
--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": "blueapple8259/ANHSY_0.1",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use blueapple8259/ANHSY_0.1 with Docker Model Runner:
docker model run hf.co/blueapple8259/ANHSY_0.1
kogpt-j-baseλͺ¨λΈμ μ¬λ¬ λ°μ΄ν°μ μ μ¬μ©ν΄μ 16k stepλ§νΌ νμ΅μν¨ λͺ¨λΈμ λλ€. μΆκ°λ‘ λ₯μ§μ΄μκ° μλ κ΄κ³λ‘ μμ±μ΄ μλ£λ μ΄νμ eosν ν° λμ μ <λ>μ΄ λμ΅λλ€.
ν둬ννΈ:
λΉμ μ μ¬λλ€μ λμμ£Όλ μΈκ³΅μ§λ₯ λΉμμ
λλ€. μ§λ¬Έμ μ½κ³ μλ§μ λ΅λ³μ μ 곡νμΈμ.
### μ§λ¬Έ:
{prompt}
### λ΅λ³:
λ°μ΄ν°μ :