Instructions to use ai-sage/GigaChat-20B-A3B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ai-sage/GigaChat-20B-A3B-instruct with Transformers:

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

pipe = pipeline("text-generation", model="ai-sage/GigaChat-20B-A3B-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ai-sage/GigaChat-20B-A3B-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ai-sage/GigaChat-20B-A3B-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ai-sage/GigaChat-20B-A3B-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai-sage/GigaChat-20B-A3B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ai-sage/GigaChat-20B-A3B-instruct

SGLang

How to use ai-sage/GigaChat-20B-A3B-instruct 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 "ai-sage/GigaChat-20B-A3B-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai-sage/GigaChat-20B-A3B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ai-sage/GigaChat-20B-A3B-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai-sage/GigaChat-20B-A3B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ai-sage/GigaChat-20B-A3B-instruct with Docker Model Runner:
```
docker model run hf.co/ai-sage/GigaChat-20B-A3B-instruct
```

Почти сразу начинает повторять себя

by Ainonake - opened Dec 17, 2024

Discussion

Ainonake

Dec 17, 2024

Repetition Penalty не помогает. Пробовал запускать с 4bit bitsandbytes и Q8 LLama.cpp - с LLama.cpp качество должно быть по-сути такое же как и в fp16.

vltnmmdv

ai-sage org Feb 3, 2025

Возможно, у вас возникли проблемы в chat template

Мы подготовили GGUF и ollama репозиторий, можете попробовать использовать модель оттуда?

• GGUF версии (bf16, q8, q6, q5, q4)
• Ollama (bf16, q8, q6, q5, q4)

Еще можно запускать в lm-studio, вот небольшой гайд.

explorerklg

Nov 18, 2025

У меня тоже начинает повотрять себя. Проблема в chat template. В llamacpp-server нет чат-темплейта для вашей модели но врод еесть возможност ьиспользовать кастомный с помощью параметра --chat-template-file . Не могли бы вы опубликовать chat-template для запуска модели?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment