Instructions to use Rakshinrules/Raksh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rakshinrules/Raksh with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Rakshinrules/Raksh")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Rakshinrules/Raksh", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Rakshinrules/Raksh with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Rakshinrules/Raksh" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Rakshinrules/Raksh", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Rakshinrules/Raksh
- SGLang
How to use Rakshinrules/Raksh 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 "Rakshinrules/Raksh" \ --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": "Rakshinrules/Raksh", "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 "Rakshinrules/Raksh" \ --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": "Rakshinrules/Raksh", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Rakshinrules/Raksh with Docker Model Runner:
docker model run hf.co/Rakshinrules/Raksh
|
Download README.md from Rakshinrules/Raksh: direct link, hf CLI and curl.
- Browser
- Download file 1.11 kB
-
https://huggingface.co/Rakshinrules/Raksh/resolve/main/README.md
- Command line
-
hf download hf://Rakshinrules/Raksh/README.md
-
curl -L -o README.md https://huggingface.co/Rakshinrules/Raksh/resolve/main/README.md
1.11 kB
metadata
license: apache-2.0
datasets:
- oscar-corpus/oscar
language:
- ru
metrics:
- rouge
- bleu
base_model:
- google-t5/t5-base
- google-t5/t5-small
- google/flan-t5-large
pipeline_tag: text-generation
library_name: transformers
tags:
- russian
- text-generation
- chatbot
- nlp
Название модели: Rakshinrules/Raksh
Описание
Эта модель предназначена для выполнения задач генерации текста на русском языке. Она разработана с использованием предобученной модели Hugging Face и оптимизирована для работы с текстами средней длины.
Задачи
- text-generation: Генерация текста на основе заданного промпта.
Примеры использования
from transformers import pipeline
generator = pipeline("text-generation", model="Rakshinrules/Raksh")
response = generator("Пример запроса", max_length=100, num_return_sequences=1)
print(response)