Instructions to use theprint/Llama3.2-3B-Explained with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theprint/Llama3.2-3B-Explained with Transformers:

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

pipe = pipeline("text-generation", model="theprint/Llama3.2-3B-Explained")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("theprint/Llama3.2-3B-Explained")
model = AutoModelForCausalLM.from_pretrained("theprint/Llama3.2-3B-Explained", device_map="auto")
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 theprint/Llama3.2-3B-Explained with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "theprint/Llama3.2-3B-Explained"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theprint/Llama3.2-3B-Explained",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/theprint/Llama3.2-3B-Explained

SGLang

How to use theprint/Llama3.2-3B-Explained 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 "theprint/Llama3.2-3B-Explained" \
    --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": "theprint/Llama3.2-3B-Explained",
		"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 "theprint/Llama3.2-3B-Explained" \
        --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": "theprint/Llama3.2-3B-Explained",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use theprint/Llama3.2-3B-Explained with Docker Model Runner:
```
docker model run hf.co/theprint/Llama3.2-3B-Explained
```

Llama3.2-3B-Explained / README.md

theprint

Upload README.md with huggingface_hub

4a3e60f verified 4 months ago

preview code

Raw

History Blame Contribute Delete

1.62 kB

metadata

base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
  - fine-tuned
  - lora
  - sft
  - auto-sft
language:
  - en
library_name: transformers

Llama3.2-3B-Explained

A fine-tuned version of meta-llama/Llama-3.2-3B-Instruct trained on Explained 0.41k alpaca data using Auto-SFT — an automated hyperparameter search and supervised fine-tuning pipeline.

The base model was adapted to follow the style and content of the Explained 0.41k alpaca dataset. Expect improved performance on tasks similar to those represented in the training data.

Model Details

Property	Value
Base model	`meta-llama/Llama-3.2-3B-Instruct`
Training data	`data/Explained-0.41k-alpaca.json`
Fine-tuning epochs	2
Fine-tuning date	2026-03-25
Fine-tuning method	LoRA (merged to full 16-bit)

Training Hyperparameters

LoRA

Parameter	Value
`r`	`4`
`alpha`	`8`
`dropout`	`0.0`
`target_modules`	`['q_proj', 'v_proj', 'k_proj', 'o_proj']`

Training

Parameter	Value
`learning_rate`	`1e-05`
`batch_size`	`1`
`gradient_accumulation_steps`	`2`
`warmup_ratio`	`0.0`
`max_seq_length`	`512`

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model     = AutoModelForCausalLM.from_pretrained("theprint/Llama3.2-3B-Explained")
tokenizer = AutoTokenizer.from_pretrained("theprint/Llama3.2-3B-Explained")

Generated by Auto-SFT