Instructions to use Xalk07/KSTU_T-lite-2.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xalk07/KSTU_T-lite-2.1-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Xalk07/KSTU_T-lite-2.1-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Xalk07/KSTU_T-lite-2.1-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Xalk07/KSTU_T-lite-2.1-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Xalk07/KSTU_T-lite-2.1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xalk07/KSTU_T-lite-2.1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xalk07/KSTU_T-lite-2.1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

SGLang

How to use Xalk07/KSTU_T-lite-2.1-GGUF 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 "Xalk07/KSTU_T-lite-2.1-GGUF" \
    --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": "Xalk07/KSTU_T-lite-2.1-GGUF",
		"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 "Xalk07/KSTU_T-lite-2.1-GGUF" \
        --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": "Xalk07/KSTU_T-lite-2.1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Xalk07/KSTU_T-lite-2.1-GGUF with Ollama:
```
ollama run hf.co/Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Xalk07/KSTU_T-lite-2.1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Xalk07/KSTU_T-lite-2.1-GGUF with Docker Model Runner:
```
docker model run hf.co/Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M
```

Lemonade

How to use Xalk07/KSTU_T-lite-2.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.KSTU_T-lite-2.1-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Xalk07/KSTU_T-lite-2.1-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Xalk07/KSTU_T-lite-2.1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Xalk07/KSTU_T-lite-2.1-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Русский | English

Русский

В этом репозитории содержится KSTU_T-lite-2.1, сконвертированная в GGUF формат с помощью llama.cpp. Оригинальная модель тут: Xalk07/KSTU_T-lite-2.1

KSTU_T-lite-2.1 - это дообученная модель на основе T-lite-it-2.1 от Т-банка. Предназначена для помощи в поиске и выдаче информации об университетском комплексе КГТУ, Россия. В университетский комплекс входит четыре образовательных организации: Калининградский Государственный Технический Университет (КГТУ), Балтийская Государственная Академия Рыбопромыслового Флота (БГАРФ), Калининградский Морской Рыбопромышленный Колледж (КМРК) и Санкт-Петербургский Морской Рыбопромышленный Колледж (СПбМРК).

Модель обучалась в 2 этапа: дополнение предложения (2 эпохи) и обучения инструкциям (3 эпохи). И знает о событиях до второй половины 2025 года.

Метрики:

Метрики	1 этап (2 эпохи)	2 этап (3 эпохи)
ROUGE-1	0,0406	0,0602
ROUGE-2	0,0037	0,0238
ROUGE-L	0,0343	0,0596
PRECISION	0,1314	0,1798
RECALL	0,1372	0,2138
F1	0,1203	0,1774

Сравнение с другим проектом от Донецкого Государственного университета:

Метрики	KSTU_T-lite-2.1 5 эпох	Ассистент Донецкого Государственного университета LLaMA-3.1-8b 25 эпох
ROUGE-1	0,0602	0,1331
ROUGE-2	0,0238	0,0721
ROUGE-L	0,0596	0,1320
PRECISION	0,1798	-
RECALL	0,2138	-
F1	0,1774	-

Использование: Вы можете использовать квантизированные варианты, оригинальную модель или интерактивное пространство.

❗Квантизированные варианты вы можете легко запустить через LM Studio или другие подобные программы. Для взаимодействия с моделью, достаточно скачать только 1 файл. Больше по размеру - лучше. Но выбирайте изходя из своих аппаратных возможностей.

ФОРМАТ	РАЗМЕР	ФАЙЛ
BF16	15.26 GB	model-KSTU_T-lite-2.1-bf16.gguf
Q8_0	8.11 GB	model-KSTU_T-lite-2.1-Q8_0.gguf
Q6_K	6.26 GB	model-KSTU_T-lite-2.1-Q6_K.gguf
Q5_K_M	5.45 GB	model-KSTU_T-lite-2.1-Q5_K_M.gguf
Q5_K_S	5.33 GB	model-KSTU_T-lite-2.1-Q5_K_S.gguf
Q4_K_M	4.68 GB	model-KSTU_T-lite-2.1-Q4_K_M.gguf
Q4_K_S	4.47 GB	model-KSTU_T-lite-2.1-Q4_K_S.gguf
Q3_K_L	4.13 GB	model-KSTU_T-lite-2.1-Q3_K_L.gguf
Q3_K_M	3.84 GB	model-KSTU_T-lite-2.1-Q3_K_M.gguf
Q3_K_S	3.51 GB	model-KSTU_T-lite-2.1-Q3_K_S.gguf
Q2_K	3.06 GB	model-KSTU_T-lite-2.1-Q2_K.gguf

Для более точных ответов используйте RAG и/или вызов инструментов.

Подробнее о модели можно будет узнать на конференциях и в статьях. (Будут добавляться в описание карточки)

English

This repository contains KSTU_T-lite-2.1, converted to GGUF format using llama.cpp. The original model is here: Xalk07/KSTU_T-lite-2.1

KSTU_T-lite-2.1 is a model fine-tuned from T-lite-it-2.1 by T-Bank. It is designed to assist in retrieving and providing information about the KSTU university complex in Russia. The university complex comprises four educational institutions: Kaliningrad State Technical University (KSTU), the Baltic Fishing Fleet State Academy (BFFSA), the Kaliningrad Marine Fishing College (KMFC), and the St. Petersburg Marine Fishing College (SPMFC).

The model was trained in two stages: sentence completion (2 epochs) and instruction tuning (3 epochs). And it knows about events up to the second half of 2025.

Metrics:

Metrics	Stage 1 (2 epochs)	Stage 2 (3 epochs)
ROUGE-1	0.0406	0.0602
ROUGE-2	0.0037	0.0238
ROUGE-L	0.0343	0.0596
PRECISION	0.1314	0.1798
RECALL	0.1372	0.2138
F1	0.1203	0.1774

Comparison with another project from Donetsk State University:

Metrics	KSTU_T-lite-2.1 5 epochs	Donetsk State University Assistant LLaMA-3.1-8b 25 epochs
ROUGE-1	0.0602	0.1331
ROUGE-2	0.0238	0.0721
ROUGE-L	0.0596	0.1320
PRECISION	0.1798	-
RECALL	0.2138	-
F1	0.1774	-

Usage: You can use quantized versions, the original model, or an interactive space.

❗You can easily run quantized versions using LM Studio or similar programs. To interact with the model, you only need to download a single file. Larger files generally offer better performance, but you should make your choice based on your hardware capabilities.

FORMAT	SIZE	FILE
BF16	15.26 GB	model-KSTU_T-lite-2.1-bf16.gguf
Q8_0	8.11 GB	model-KSTU_T-lite-2.1-Q8_0.gguf
Q6_K	6.26 GB	model-KSTU_T-lite-2.1-Q6_K.gguf
Q5_K_M	5.45 GB	model-KSTU_T-lite-2.1-Q5_K_M.gguf
Q5_K_S	5.33 GB	model-KSTU_T-lite-2.1-Q5_K_S.gguf
Q4_K_M	4.68 GB	model-KSTU_T-lite-2.1-Q4_K_M.gguf
Q4_K_S	4.47 GB	model-KSTU_T-lite-2.1-Q4_K_S.gguf
Q3_K_L	4.13 GB	model-KSTU_T-lite-2.1-Q3_K_L.gguf
Q3_K_M	3.84 GB	model-KSTU_T-lite-2.1-Q3_K_M.gguf
Q3_K_S	3.51 GB	model-KSTU_T-lite-2.1-Q3_K_S.gguf
Q2_K	3.06 GB	model-KSTU_T-lite-2.1-Q2_K.gguf

For more accurate answers, use RAG and/or tool calling.

More information about the model will be available at conferences and in articles. (These will be added to the card description.)

Downloads last month: -

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Xalk07/KSTU_T-lite-2.1-GGUF

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

t-tech/T-lite-it-2.1

Finetuned

Xalk07/KSTU_T-lite-2.1

Quantized

(1)

this model