Instructions to use WQchoi/QLoRA_test3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WQchoi/QLoRA_test3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="WQchoi/QLoRA_test3")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("WQchoi/QLoRA_test3") model = AutoModelForCausalLM.from_pretrained("WQchoi/QLoRA_test3") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use WQchoi/QLoRA_test3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "WQchoi/QLoRA_test3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "WQchoi/QLoRA_test3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/WQchoi/QLoRA_test3
- SGLang
How to use WQchoi/QLoRA_test3 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "WQchoi/QLoRA_test3" \ --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": "WQchoi/QLoRA_test3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
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 "WQchoi/QLoRA_test3" \ --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": "WQchoi/QLoRA_test3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use WQchoi/QLoRA_test3 with Docker Model Runner:
docker model run hf.co/WQchoi/QLoRA_test3
args=TrainingArguments(
output_dir="C:/Users/tjrja/OneDrive/๋ฐํ ํ๋ฉด/finet/checkpoint4",
load_best_model_at_end=True,
auto_find_batch_size=True,
gradient_accumulation_steps=1,
warmup_ratio=0.1,
num_train_epochs=10,
learning_rate=1e-4,
max_grad_norm=0.5,
weight_decay=0.0001,
fp16=True,
optim="paged_adamw_32bit",
lr_scheduler_type="constant",
logging_steps=264,
evaluation_strategy="epoch",
eval_steps=1,
save_strategy="epoch",
save_steps=10,
)
- Downloads last month
- 3