Instructions to use GalvinNguyen/vian_ai_shop_small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GalvinNguyen/vian_ai_shop_small with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-4b-it")
model = PeftModel.from_pretrained(base_model, "GalvinNguyen/vian_ai_shop_small")

Transformers

How to use GalvinNguyen/vian_ai_shop_small with Transformers:

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

pipe = pipeline("text-generation", model="GalvinNguyen/vian_ai_shop_small")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("GalvinNguyen/vian_ai_shop_small")
model = AutoModelForMultimodalLM.from_pretrained("GalvinNguyen/vian_ai_shop_small")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GalvinNguyen/vian_ai_shop_small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GalvinNguyen/vian_ai_shop_small

SGLang

How to use GalvinNguyen/vian_ai_shop_small 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 "GalvinNguyen/vian_ai_shop_small" \
    --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": "GalvinNguyen/vian_ai_shop_small",
		"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 "GalvinNguyen/vian_ai_shop_small" \
        --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": "GalvinNguyen/vian_ai_shop_small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GalvinNguyen/vian_ai_shop_small with Docker Model Runner:
```
docker model run hf.co/GalvinNguyen/vian_ai_shop_small
```

Model Card for Vian ai Fine-Tuned

Model Details

Model Description

Developed by: Glavinnguyen
Model type: Text Generation / Multimodal (Text/Vision/Audio Interface)
Language(s) (NLP): Vietnamese (Primary), English (Primary)
License: mit
Finetuned from model: google/gemma-3-4b-it

Model Sources

Repository: [More Information Needed]

Uses

Direct Use

This model is specifically fine-tuned on a small-scale dataset to standardize response formatting, style, and structure. It natively retains the advanced deep reasoning mechanisms (<|think|>) and inherent logical problem-solving capabilities of the base Gemma 3 architecture.

Out-of-Scope Use

The model should not be used for tasks requiring extensive broad-domain knowledge expansion outside the scope of the training dataset without human supervision. The fine-tuning process was focused on structuring behavioral output rather than massive knowledge injection.

Training Details

Training Data

The model was trained on a highly curated, high-quality alignment dataset.

Training Procedure

Training was conducted utilizing the QLoRA (Quantized Low-Rank Adaptation) method to minimize hardware resource consumption while aggressively preserving the base model's pre-trained weights.

Training Hyperparameters

The hyperparameters were carefully optimized for an ultra-small dataset to prevent catastrophic overfitting and achieve an ideal convergence point:

Training regime: QLoRA (FP16/BF16 Mixed Precision)
Learning Rate: 2e-4 to 1e-5 (Low Learning Rate)
Per Device Train Batch Size: 1
Gradient Accumulation Steps: 32 (Global Batch Size = 32)
Number of Train Epochs: 1 to 2
Max Length: 256 - 2048 tokens (Allocated to safeguard the generation of <|think|> tokens)
Optimizer: AdamW
LR Scheduler Type: Cosine / Constant
LoRA Rank (r): 4 or 8
LoRA Alpha ($\alpha$): 8 or 16

Speeds, Sizes, Times

Final Training Loss: 0.69 (The sweet spot convergence for low-sample fine-tuning—balancing structural alignment with base intelligence retention).
VRAM Consumption: ~2.2 GB (When running on a 4-bit Q4_0 execution profile).

Technical Specifications

Model Architecture and Objective

Built upon Google's next-generation Gemma 3 architecture, featuring integrated Quantization Aware Training (QAT) and an intrinsic multi-token prediction (MTP) engine. The model leverages an internal step-by-step reasoning loop before routing structural text outputs via designated generation tags.

Model Card Contact

Contact: Glavinnguyen

Framework versions

PEFT 0.19.1

Downloads last month: 756

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for GalvinNguyen/vian_ai_shop_small

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Adapter

(412)

this model