Instructions to use omni-devel/QA-Gen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use omni-devel/QA-Gen with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="omni-devel/QA-Gen")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("omni-devel/QA-Gen") model = AutoModelForSeq2SeqLM.from_pretrained("omni-devel/QA-Gen") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use omni-devel/QA-Gen with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "omni-devel/QA-Gen" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "omni-devel/QA-Gen", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/omni-devel/QA-Gen
- SGLang
How to use omni-devel/QA-Gen 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 "omni-devel/QA-Gen" \ --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": "omni-devel/QA-Gen", "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 "omni-devel/QA-Gen" \ --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": "omni-devel/QA-Gen", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use omni-devel/QA-Gen with Docker Model Runner:
docker model run hf.co/omni-devel/QA-Gen
YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
Встроенный инференс генерирует плохо. Запускайте модель локально
T5 для генерации пары вопрос-ответ на русском языке. Использование:
import torch
from transformers import AutoModelForSeq2SeqLM, T5Tokenizer
model_name = "PyWebSol/QA-Gen"
tokenizer = T5Tokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
def generate(text, **kwargs):
inputs = tokenizer(text, return_tensors='pt')
with torch.no_grad():
hypotheses = model.generate(**inputs, num_beams=1, **kwargs, max_new_tokens=512)
print(hypotheses)
return tokenizer.decode(hypotheses[0], skip_special_tokens=True)
qa = generate(
"К особым префектурам можно отнести Токио, Киото, Осаку и Хоккайдо. В период Эдо (1603—1867), сёгунат установил 9 городских районов, которыми управляли чиновники из центра (奉行支配地), и 302 районных города, которыми управляли городские чиновники (郡代支配地). С наступлением эпохи Мэйдзи 9 городских центров были превращены в округа фу, а 302 районных города — в префектуры кэн. В 1871 г., после административной реформы, в Японии было установлено 3 городских префектур фу — Токио, Киото и Осака. В 1943 г. городская префектура Токио была переименована в столицу то (хотя закона о столице утверждено не было)."
).split(" <|split|> ")
question, answer = qa
print(f"Вопрос: {question}")
print(f"Ответ: {answer}")
# Вопрос: В каком период было установлено 3 городских префектур фу — Токио, Киото и Осака?
# Ответ: В 1871 году.
Модель может быть полезна для автоматизированной генерации наборов данных по тексту для обучения других NLP моделей.
Телеграм бот для фильтрации спама в чатах: https://t.me/omni_antispam_bot
- Downloads last month
- 10