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

Libraries

How to use AvitoTech/avibe with Transformers:

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

pipe = pipeline("text-generation", model="AvitoTech/avibe")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AvitoTech/avibe")
model = AutoModelForCausalLM.from_pretrained("AvitoTech/avibe")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AvitoTech/avibe with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AvitoTech/avibe

SGLang

How to use AvitoTech/avibe 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 "AvitoTech/avibe" \
    --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": "AvitoTech/avibe",
		"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 "AvitoTech/avibe" \
        --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": "AvitoTech/avibe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

ElijahKamski

ariG23498 HF Staff commited on Oct 30, 2025

Commit

b24a7cd

verified ·

1 Parent(s): 7e2be91

Adding `transformers` as the library name (#3)

Browse files

- Adding `transformers` as the library name (42f86d473301f7f520b5ec06fc46732d75aaedba)

Co-authored-by: Aritra Roy Gosthipaty <ariG23498@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -6,6 +6,7 @@ language:
 base_model:
 - Qwen/Qwen3-8B
 pipeline_tag: text-generation
 ---
 A-vibe это большая языковая модель, созданная Авито Тех, дочерней технологической компанией Авито, на базе открытой модели Qwen3-8B-Base.
 Мы адаптировали Qwen3-8B-Base под русский язык и домен Авито с помощью нескольких шагов

 base_model:
 - Qwen/Qwen3-8B
 pipeline_tag: text-generation
+library_name: transformers
 ---
 A-vibe это большая языковая модель, созданная Авито Тех, дочерней технологической компанией Авито, на базе открытой модели Qwen3-8B-Base.
 Мы адаптировали Qwen3-8B-Base под русский язык и домен Авито с помощью нескольких шагов