Instructions to use longtimedevs/Ru-Small-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use longtimedevs/Ru-Small-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="longtimedevs/Ru-Small-Instruct")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("longtimedevs/Ru-Small-Instruct")
model = AutoModelForCausalLM.from_pretrained("longtimedevs/Ru-Small-Instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use longtimedevs/Ru-Small-Instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/longtimedevs/Ru-Small-Instruct

SGLang

How to use longtimedevs/Ru-Small-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 "longtimedevs/Ru-Small-Instruct" \
    --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": "longtimedevs/Ru-Small-Instruct",
		"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 "longtimedevs/Ru-Small-Instruct" \
        --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": "longtimedevs/Ru-Small-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use longtimedevs/Ru-Small-Instruct with Docker Model Runner:
```
docker model run hf.co/longtimedevs/Ru-Small-Instruct
```

longtimedevs commited on 16 days ago

Commit

3446842

verified ·

1 Parent(s): 73e7602

Update INFO.md

Browse files

Files changed (1) hide show

INFO.md +1 -1

INFO.md CHANGED Viewed

@@ -26,7 +26,7 @@ This model (**Ru-Small-Instruct**) and its associated ecosystem are developed an
 ## <svg xmlns="http://www.w3.org/2000/svg" width="22" height="22" viewBox="0 0 24 24" fill="none" stroke="#10b981" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="vertical-align: -3px; margin-right: 8px;"><polygon points="12 2 2 7 12 12 22 7 12 2"/><polyline points="2 17 12 22 22 17"/><polyline points="2 12 12 17 22 12"/></svg>About Ru-Small-Instruct
 * **Hugging Face Repository:** [longtimedevs/Ru-Small-Instruct](https://huggingface.co/longtimedevs/Ru-Small-Instruct)
 * **License:** MIT License
-* **Scope:** Lightweight, sovereign ~0.2B parameter Russian language model optimized for local inference, micro-deployments, and open-source research.
 ---

 ## <svg xmlns="http://www.w3.org/2000/svg" width="22" height="22" viewBox="0 0 24 24" fill="none" stroke="#10b981" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="vertical-align: -3px; margin-right: 8px;"><polygon points="12 2 2 7 12 12 22 7 12 2"/><polyline points="2 17 12 22 22 17"/><polyline points="2 12 12 17 22 12"/></svg>About Ru-Small-Instruct
 * **Hugging Face Repository:** [longtimedevs/Ru-Small-Instruct](https://huggingface.co/longtimedevs/Ru-Small-Instruct)
 * **License:** MIT License
+* **Scope:** Lightweight, sovereign ~0.1B parameter Russian language model optimized for local inference, micro-deployments, and open-source research.
 ---