Instructions to use s1nan/llama-3.2-3b-qlora-myproject with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use s1nan/llama-3.2-3b-qlora-myproject with Transformers:

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

pipe = pipeline("text-generation", model="s1nan/llama-3.2-3b-qlora-myproject")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("s1nan/llama-3.2-3b-qlora-myproject", device_map="auto")

PEFT
How to use s1nan/llama-3.2-3b-qlora-myproject with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use s1nan/llama-3.2-3b-qlora-myproject with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "s1nan/llama-3.2-3b-qlora-myproject"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "s1nan/llama-3.2-3b-qlora-myproject",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/s1nan/llama-3.2-3b-qlora-myproject

SGLang

How to use s1nan/llama-3.2-3b-qlora-myproject 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 "s1nan/llama-3.2-3b-qlora-myproject" \
    --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": "s1nan/llama-3.2-3b-qlora-myproject",
		"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 "s1nan/llama-3.2-3b-qlora-myproject" \
        --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": "s1nan/llama-3.2-3b-qlora-myproject",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use s1nan/llama-3.2-3b-qlora-myproject with Docker Model Runner:
```
docker model run hf.co/s1nan/llama-3.2-3b-qlora-myproject
```

🦙 Llama 3.2 3B — QLoRA Fine-Tuned

Parameter-efficient instruction fine-tuning of unsloth/Llama-3.2-3B-Instruct using QLoRA.

✨ Highlights

4-bit quantized base model
LoRA-based parameter-efficient fine-tuning
NF4 quantization
Unsloth optimized training
Hugging Face TRL SFTTrainer
PEFT adapters
Designed for low-VRAM experimentation

🧠 Model Overview

This model is a QLoRA fine-tuned adapter based on:

unsloth/Llama-3.2-3B-Instruct

The base model remains frozen while lightweight LoRA adapters are trained on the instruction dataset.

Training Pipeline

Pretrained Llama 3.2 3B
        │
        ▼
   4-bit Quantization
        │
        ▼
   Frozen Base Model
        │
        ▼
      LoRA
        │
        ▼
  Supervised Fine-Tuning
        │
        ▼
  Fine-Tuned Adapter

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for s1nan/llama-3.2-3b-qlora-myproject

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

unsloth/Llama-3.2-3B-Instruct

Adapter

(450)

this model

s1nan
/

llama-3.2-3b-qlora-myproject

🦙 Llama 3.2 3B — QLoRA Fine-Tuned

✨ Highlights

🧠 Model Overview

Training Pipeline

Model tree for s1nan/llama-3.2-3b-qlora-myproject

Dataset used to train s1nan/llama-3.2-3b-qlora-myproject