Instructions to use dwaru/RuAdaptGPT2Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dwaru/RuAdaptGPT2Small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dwaru/RuAdaptGPT2Small")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dwaru/RuAdaptGPT2Small") model = AutoModelForCausalLM.from_pretrained("dwaru/RuAdaptGPT2Small") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use dwaru/RuAdaptGPT2Small with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dwaru/RuAdaptGPT2Small" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dwaru/RuAdaptGPT2Small", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dwaru/RuAdaptGPT2Small
- SGLang
How to use dwaru/RuAdaptGPT2Small 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 "dwaru/RuAdaptGPT2Small" \ --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": "dwaru/RuAdaptGPT2Small", "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 "dwaru/RuAdaptGPT2Small" \ --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": "dwaru/RuAdaptGPT2Small", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dwaru/RuAdaptGPT2Small with Docker Model Runner:
docker model run hf.co/dwaru/RuAdaptGPT2Small
Модель созданная студентами ДГТУ "Школа Икс" для задач по генерации адаптированого текста на основе начального текста
Был использован промпт: 'Адапитруй текст {text} на уровень по CEFR: {level} Адаптированый текст: {target}'
Модель ai-forever/rugpt3small_based_on_gpt2 дообученая на датасете RuAdapt и RuSimpleSentEval подогнанным под формат RuAdapt
Ссылка на колаб: https://colab.research.google.com/drive/1wmfBC59Ju99g0TBfoWVO-24fy2mSPfMM?usp=sharing
- Downloads last month
- 4
Model tree for dwaru/RuAdaptGPT2Small
Base model
ai-forever/rugpt3small_based_on_gpt2