Text Generation
Transformers
Safetensors
Indonesian
gpt2
dpo
lora
preference-optimization
text-generation-inference
Instructions to use RantiRepo/gpt2-DPO-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RantiRepo/gpt2-DPO-LoRA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RantiRepo/gpt2-DPO-LoRA")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("RantiRepo/gpt2-DPO-LoRA") model = AutoModelForCausalLM.from_pretrained("RantiRepo/gpt2-DPO-LoRA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use RantiRepo/gpt2-DPO-LoRA with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RantiRepo/gpt2-DPO-LoRA" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RantiRepo/gpt2-DPO-LoRA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/RantiRepo/gpt2-DPO-LoRA
- SGLang
How to use RantiRepo/gpt2-DPO-LoRA 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 "RantiRepo/gpt2-DPO-LoRA" \ --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": "RantiRepo/gpt2-DPO-LoRA", "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 "RantiRepo/gpt2-DPO-LoRA" \ --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": "RantiRepo/gpt2-DPO-LoRA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use RantiRepo/gpt2-DPO-LoRA with Docker Model Runner:
docker model run hf.co/RantiRepo/gpt2-DPO-LoRA
GPT-2 DPO LoRA
Fine-tuning model gpt2 menggunakan Direct Preference Optimization (DPO) dengan LoRA.
Base Model
gpt2
Training
- Method: DPO
- LoRA Rank: 16
- LoRA Alpha: 32
- Epoch: 2
- Learning Rate: 0.0001
- Beta: 0.1
- Max Sequence Length: 1024
Dataset
IndonesiaAI/dpo-dataset
sampling 20.000 data saja yang diambil,
Dataset digunakan dalam format:
- Prompt
- Chosen response
- Rejected response
Training Objective
Model dioptimalkan agar memberikan preferensi lebih tinggi terhadap response chosen dibandingkan response rejected.
- Downloads last month
- 243
Model tree for RantiRepo/gpt2-DPO-LoRA
Base model
openai-community/gpt2