Instructions to use SiberiaSoft/ruGPT3_medium_chitchat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SiberiaSoft/ruGPT3_medium_chitchat with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SiberiaSoft/ruGPT3_medium_chitchat")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SiberiaSoft/ruGPT3_medium_chitchat", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SiberiaSoft/ruGPT3_medium_chitchat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SiberiaSoft/ruGPT3_medium_chitchat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SiberiaSoft/ruGPT3_medium_chitchat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SiberiaSoft/ruGPT3_medium_chitchat

SGLang

How to use SiberiaSoft/ruGPT3_medium_chitchat 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 "SiberiaSoft/ruGPT3_medium_chitchat" \
    --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": "SiberiaSoft/ruGPT3_medium_chitchat",
		"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 "SiberiaSoft/ruGPT3_medium_chitchat" \
        --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": "SiberiaSoft/ruGPT3_medium_chitchat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SiberiaSoft/ruGPT3_medium_chitchat with Docker Model Runner:
```
docker model run hf.co/SiberiaSoft/ruGPT3_medium_chitchat
```

Модель русскозычного чат бота, работающая в режиме чит-чат (без контекста предыдущих сообщений)

Пример работы с моделью:

import torch
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained('SiberiaSoft/ruGPT3_medium_chitchat')
model = AutoModelWithLMHead.from_pretrained('SiberiaSoft/ruGPT3_medium_chitchat')
inputs = tokenizer('[FIRST] Привет [SECOND]', return_tensors='pt')
generated_token_ids = model.generate(
    **inputs,
    top_k=10,
    top_p=0.95,
    num_beams=3,
    num_return_sequences=5,
    do_sample=True,
    no_repeat_ngram_size=2,
    temperature=1.0,
    repetition_penalty=1.2,
    length_penalty=1.0,
    eos_token_id=50257,
    max_length = 400
)
generation = [tokenizer.decode(sample_token_ids) for sample_token_ids in generated_token_ids]
print(generation)

Downloads last month: 227