Instructions to use Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 with fastai:

from huggingface_hub import from_pretrained_fastai

learn = from_pretrained_fastai("Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 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 Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2
# Run inference directly in the terminal:
llama cli -hf Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2
# Run inference directly in the terminal:
llama cli -hf Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2

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 Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2
# Run inference directly in the terminal:
./llama-cli -hf Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2

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 Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2

Use Docker

docker model run hf.co/Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2

LM Studio
Jan

vLLM

How to use Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2

Ollama
How to use Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 with Ollama:
```
ollama run hf.co/Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2
```

Unsloth Studio

How to use Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 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 Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 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 Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 to start chatting

Docker Model Runner
How to use Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 with Docker Model Runner:
```
docker model run hf.co/Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2
```

Lemonade

How to use Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2

Run and chat with the model

lemonade run user.aidc-llm-laos-10k-gemma-3-12b-it-v2-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

A newer version of this model is available: Phonepadith/Laollm

🧠 Lao Summarization Model ສົນທະນາ - ສະຫລຸບເນື້ອຫາສຳລັບພາສາລາວ - Fine-tuned Gemma 3 12B IT (10,000 Pairs, Laos Content Input-Output)

This is a Lao language summarization model fine-tuned on the `Phonepadith/laos_word_dataset`, using the base model `google/gemma-3-12b-it`. The model is designed to generate concise summaries from Lao language text. Scope: - 📚 ສະຫລຸບຂ່າວ - 📚 ສະຫລຸບເອກະສານພາກລັດ - 📚 ສະຫລຸບກອງປະຊຸມ

🧠 Lao AIDC-10K Fine-tuned Gemma-3-12B-IT-V2

Model ID: Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2
Base Model: google/gemma-3b-it
Fine-tuned By: Phonepadith Phoummavong

📌 Model Description

This model is a fine-tuned version of Gemma-3-12B-IT-, specifically adapted to understand and generate responses in Lao language 🇱🇦. It was trained using a curated dataset of over 5,000 high-quality Lao input-output pairs, primarily focused on AIDC (Artificial Intelligence and Digital Content) topics.

Key Features:

🗣️ Fine-tuned for Lao language generation
📚 Suitable for summarization, question answering, general chat
🧠 Based on Google's powerful Gemma 3-12B Instruct model

🧾 Training Details

Detail	Value
Base Model	Gemma 3-12B Instruct
Fine-tuning Method	LoRA with PEFT (Unsloth)
Dataset	10,000 Laos supervised samples
Sequence Length	2048
Batch Size	2 (with gradient accumulation)
Optimizer	AdamW
Epochs	3–5 (early stopping enabled)
Format	GGUF (F16, Q8_0, Q4_0 available)

📥 How to Use (LM Studio)

Install LM Studio: https://lmstudio.ai
Import the Model:
- Via Hugging Face: Search for Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it
- Or drag the .gguf file into LM Studio
Set System Prompt:

📌 Model Details

Base Model: google/gemma-3-12b-it
Fine-tuned by: Phonepadith
Language: Lao (lo)
Task: Text Generation
Library: adapter-transformers
License: Apache 2.0

📊 Metrics

Evaluation Metric: BLEU score
BLEU is used to evaluate the quality of generated summaries against reference summaries in the dataset.

🛠️ How to Use

You can load and use the model with Hugging Face Transformers and adapter-transformers:


from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2"  # change to your actual model name
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

input_text = "ປັດຈຸບັນ ກອງທັບປະຊາຊົນລາວ ມີການປະກອບວັດຖຸເຕັກນິກທັນສະໄໝສົມຄວນ, ສາມາດຕອບສະໜອງ ໃຫ້ແກ່ວຽກງານປ້ອງກັນຊາດ ໃນໄລຍະໃໝ່ ໄດ້ໂດຍພື້ນຖານ; ໄດ້ປະກອບສ່ວນຢ່າງຕັ້ງໜ້າເຂົ້າໃນການປ້ອງກັນ, ຄວບຄຸມໄພພິບັດ ແລະ ຊ່ວຍເຫລືອປະຊາຊົນ ຜູ້ປະສົບໄພພິບັດທຳມະຊາດຕ່າງໆທີ່ເກີດຂຶ້ນໃນຂອບເຂດທົ່ວປະເທດ. ພ້ອມນັ້ນ, ກໍໄດ້ເປັນເຈົ້າການປະກອບສ່ວນປັບປຸງກໍ່ສ້າງພື້ນ ຖານການເມືອງ, ກໍ່ສ້າງທ່າສະໜາມສົງຄາມປະຊາຊົນ 3 ຂັ້ນ ຕິດພັນກັບວຽກງານ 3 ສ້າງ ຢູ່ທ້ອງຖິ່ນຕາມ 4 ເນື້ອໃນ 4 ຄາດໝາຍ ແລະ ສືບທອດມູນເຊື້ອຄວາມສາມັກຄີ ກັບກອງທັບປະເທດເພື່ອນມິດ ສາກົນ, ປະຕິບັດນະໂຍບາຍເພີ່ມມິດຫລຸດຜ່ອນສັດຕູ, ຮັບປະກັນສະຖຽນລະພາບ ຂອງລະບອບການ ເມືອງ, ຮັກສາຄວາມສະຫງົບປອດໄພຕາມຊາຍແດນ"
inputs = tokenizer(input_text, return_tensors="pt")
summary_ids = model.generate(**inputs, max_new_tokens=100)
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)

print(summary)

Downloads last month: 12

GGUF

Model size

13B params

Architecture

gemma3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Phonepadith/aidc-llm-laos-10k-gemma-3-12b-it-v2

Base model

google/gemma-3-12b-pt

Finetuned

google/gemma-3-12b-it

Quantized

(167)

this model

Phonepadith
/

aidc-llm-laos-10k-gemma-3-12b-it-v2