Instructions to use Just-Bax/qwen3-14b-base-uzbek-cyrillic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Just-Bax/qwen3-14b-base-uzbek-cyrillic with Transformers:

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

pipe = pipeline("text-generation", model="Just-Bax/qwen3-14b-base-uzbek-cyrillic")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Just-Bax/qwen3-14b-base-uzbek-cyrillic")
model = AutoModelForCausalLM.from_pretrained("Just-Bax/qwen3-14b-base-uzbek-cyrillic")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Just-Bax/qwen3-14b-base-uzbek-cyrillic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Just-Bax/qwen3-14b-base-uzbek-cyrillic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Just-Bax/qwen3-14b-base-uzbek-cyrillic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Just-Bax/qwen3-14b-base-uzbek-cyrillic

SGLang

How to use Just-Bax/qwen3-14b-base-uzbek-cyrillic 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 "Just-Bax/qwen3-14b-base-uzbek-cyrillic" \
    --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": "Just-Bax/qwen3-14b-base-uzbek-cyrillic",
		"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 "Just-Bax/qwen3-14b-base-uzbek-cyrillic" \
        --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": "Just-Bax/qwen3-14b-base-uzbek-cyrillic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use Just-Bax/qwen3-14b-base-uzbek-cyrillic with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Just-Bax/qwen3-14b-base-uzbek-cyrillic to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Just-Bax/qwen3-14b-base-uzbek-cyrillic to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Just-Bax/qwen3-14b-base-uzbek-cyrillic to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Just-Bax/qwen3-14b-base-uzbek-cyrillic",
    max_seq_length=2048,
)

Docker Model Runner
How to use Just-Bax/qwen3-14b-base-uzbek-cyrillic with Docker Model Runner:
```
docker model run hf.co/Just-Bax/qwen3-14b-base-uzbek-cyrillic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3-14B-Base-Uzbek-Cyrillic

Fine-tuned variant of Qwen3-14B-Base for Uzbek (Cyrillic script), trained with LoRA via Unsloth. Suited for text generation, chat, and summarization in Uzbek Cyrillic, with the base model’s multilingual capabilities preserved.

Model Overview

Property	Value
Base model	Qwen/Qwen3-14B-Base
Architecture	Transformer Decoder (Causal LM)
Parameters	14.8B
Context length	32,768 tokens
Finetuning method	LoRA (r=16, α=32, dropout=0.0)
Training framework	Unsloth
Precision	bfloat16
Languages	Uzbek (Cyrillic), multilingual

Intended Use

Natural, grammatically coherent text generation in Uzbek Cyrillic
Content generation, chat, and summarization in Uzbek
Multilingual setups and applications targeting Central Asian languages

Usage

Load and run the model with transformers or vLLM.

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Just-Bax/Qwen3-14B-Base-Uzbek-Cyrillic"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

prompt = "Ассалому алайкум! Бугунги кун ҳақида маълумот беринг."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 2

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for Just-Bax/qwen3-14b-base-uzbek-cyrillic

Base model

Qwen/Qwen3-14B-Base

Finetuned

(71)

this model

Quantizations

3 models