Instructions to use atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad with Transformers:

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

pipe = pipeline("text-generation", model="atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad")
model = AutoModelForCausalLM.from_pretrained("atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad

SGLang

How to use atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad 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 "atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad" \
    --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": "atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad",
		"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 "atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad" \
        --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": "atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad with Docker Model Runner:
```
docker model run hf.co/atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad
```

Qwen3 14B Base for Telugu: Continual pre-training only

This model is built on top of Qwen3 14B Base adapted for Telugu using 500M target language tokens sampled from MADLAD-400.

Model Details

Vocabulary: This model has no additional target vocabulary. It retains the original vocabulary of Qwen3 14B Base.
Training: This model was continually pre-trained on 500M target language tokens sampled from MADLAD-400.

Model Description

Language: Telugu
License: Apache 2.0
Fine-tuned from model: Qwen/Qwen3-14B-Base

Model Sources

Repository: https://github.com/gucci-j/chat-cve
Paper: https://arxiv.org/abs/2412.11704

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
    "atsuki-yamaguchi/Qwen3-14B-Base-te-lapt-madlad"
)
tokenizer = AutoTokenizer.from_pretrained(
    "Qwen/Qwen3-14B-Base"
)

Citation

@article{yamaguchi2025adapting,
      title={Adapting Chat Language Models Using Only Target Unlabeled Language Data}, 
      author={Atsuki Yamaguchi and Terufumi Morishita and Aline Villavicencio and Nikolaos Aletras},
      journal={Transactions on Machine Learning Research},
      issn={2835-8856},
      year={2025},
      url={https://openreview.net/forum?id=6IdoIKowfe},
      note={}
}