nlpai-lab/kullm-v2
Viewer β’ Updated β’ 153k β’ 511 β’ 77
How to use blueapple8259/ANHSY_test with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="blueapple8259/ANHSY_test") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("blueapple8259/ANHSY_test")
model = AutoModelForCausalLM.from_pretrained("blueapple8259/ANHSY_test", device_map="auto")How to use blueapple8259/ANHSY_test with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blueapple8259/ANHSY_test"
# 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_test",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/blueapple8259/ANHSY_test
How to use blueapple8259/ANHSY_test with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "blueapple8259/ANHSY_test" \
--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_test",
"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_test" \
--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_test",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use blueapple8259/ANHSY_test with Docker Model Runner:
docker model run hf.co/blueapple8259/ANHSY_test
kogpt-j-baseλͺ¨λΈμ λ°μ΄ν°μ μΈκ°μ§λ₯Ό μ¬μ©ν΄μ 45k step(0.27 epoch)λ§νΌ νμ΅μν¨ λͺ¨λΈμ λλ€.
ν둬ννΈ:
<|im_start|>system
λΉμ μ μ¬λλ€μ λμμ£Όλ μΈκ³΅μ§λ₯ λΉμμ
λλ€. μ§λ¬Έμ μ½κ³ μλ§μ λ΅λ³μ μ 곡νμΈμ.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
λ°μ΄ν°μ :