Instructions to use IlyaGusev/saiga_gemma2_9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IlyaGusev/saiga_gemma2_9b with Transformers:

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

pipe = pipeline("text-generation", model="IlyaGusev/saiga_gemma2_9b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("IlyaGusev/saiga_gemma2_9b")
model = AutoModelForCausalLM.from_pretrained("IlyaGusev/saiga_gemma2_9b")
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 IlyaGusev/saiga_gemma2_9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IlyaGusev/saiga_gemma2_9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IlyaGusev/saiga_gemma2_9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IlyaGusev/saiga_gemma2_9b

SGLang

How to use IlyaGusev/saiga_gemma2_9b 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 "IlyaGusev/saiga_gemma2_9b" \
    --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": "IlyaGusev/saiga_gemma2_9b",
		"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 "IlyaGusev/saiga_gemma2_9b" \
        --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": "IlyaGusev/saiga_gemma2_9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IlyaGusev/saiga_gemma2_9b with Docker Model Runner:
```
docker model run hf.co/IlyaGusev/saiga_gemma2_9b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Saiga/Gemma2 9B, Russian Gemma-2-based chatbot

Based on Gemma-2 9B Instruct.

Prompt format

Gemma-2 prompt format:

<start_of_turn>system
Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.<end_of_turn>
<start_of_turn>user
Как дела?<end_of_turn>
<start_of_turn>model
Отлично, а у тебя?<end_of_turn>
<start_of_turn>user
Шикарно. Как пройти в библиотеку?<end_of_turn>
<start_of_turn>model

Code example

# Исключительно ознакомительный пример.
# НЕ НАДО ТАК ИНФЕРИТЬ МОДЕЛЬ В ПРОДЕ.
# См. https://github.com/vllm-project/vllm или https://github.com/huggingface/text-generation-inference

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig

MODEL_NAME = "IlyaGusev/saiga_gemma2_10b"

model = AutoModelForCausalLM.from_pretrained(
    MODEL_NAME,
    load_in_8bit=True,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
model.eval()

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
print(generation_config)

inputs = ["Почему трава зеленая?", "Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч"]
for query in inputs:
    prompt = tokenizer.apply_chat_template([{
        "role": "user",
        "content": query
    }], tokenize=False, add_generation_prompt=True)
    data = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
    data = {k: v.to(model.device) for k, v in data.items()}
    output_ids = model.generate(**data, generation_config=generation_config)[0]
    output_ids = output_ids[len(data["input_ids"][0]):]
    output = tokenizer.decode(output_ids, skip_special_tokens=True).strip()
    print(query)
    print(output)
    print()
    print("==============================")
    print()