Instructions to use demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation")

llama-cpp-python

How to use demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation",
	filename="Llama-3.2-3B-Instruct-PEFT-code-generation.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0
# Run inference directly in the terminal:
llama-cli -hf demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0
# Run inference directly in the terminal:
llama-cli -hf demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0

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 demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0

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 demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0

Use Docker

docker model run hf.co/demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0

LM Studio
Jan
Ollama
How to use demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation with Ollama:
```
ollama run hf.co/demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0
```

Unsloth Studio

How to use demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation 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 demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation 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 demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation to start chatting

How to use demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation with Docker Model Runner:
```
docker model run hf.co/demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0
```

Lemonade

How to use demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation:Q8_0

Run and chat with the model

lemonade run user.Llama-3.2-3B-Instruct-PEFT-code-generation-Q8_0

List all available models

lemonade list

See axolotl config

axolotl version: 0.10.0

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

load_in_8bit: true
load_in_4bit: false

datasets:
  - path: ./data/train_openai_response_transformed.jsonl
    type: chat_template

    field_messages: messages
    message_property_mappings:
      role: role
      content: content

val_file: ./data/val_openai_response_transformed.jsonl
val_set_size: 0.0
output_dir: ./outputs/cf-llm-finetune-llama-3.2-3b-lora

adapter: lora
lora_model_dir:

sequence_len: 4096
sample_packing: false
eval_sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4

optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: false

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: false

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:
  pad_token: "<|end_of_text|>"

Llama-3.2-3B-Instruct-PEFT-code-generation

This model is a fine tuned meta-llama/Llama-3.2-3B-Instruct on a synthetic dataset of C++ → Python code translations from Codeforces.

📦 GitHub repo: DemoVersion/cf-llm-finetune

📑 Dataset Creation DATASET.md

📑 Training TRAIN.md

📚 Dataset on Hugging Face: demoversion/cf-cpp-to-python-code-generation

For dataset generation, training, and inference check the Github repo.

📚 Main medium article: Toward fine-tuning Llama 3.2 using PEFT for Code Generation

📚 Medium article for inference with GGUF format: How to inference with GGUF format

Model description

A lightweight LLaMA 3.2 model fine-tuned for competitive programming code translation, from ICPC-style C++ to Python using LoRA adapters.

Intended uses & limitations

Use for:

Translating competitive programming C++ solutions to Python
Code understanding in educational or automation tools

Limitations:

Not general-purpose code translation
Python outputs are synthetically generated using GPT-4.1
Focused only on ICPC-style problems

Training and evaluation data

Training and Evaluation data:
🧾 demoversion/cf-cpp-to-python-code-generation

Built from:

C++ submissions were filtered and paired with GPT-4.1-generated Python translations. Dataset split: 1,400 train / 300 val / 300 test. To underestand how the dataset was created check DATASET.md

Training procedure

Adapter: LoRA (r=32, alpha=16, dropout=0.05)
Optimizer: adamw_bnb_8bit
LR: 2e-4, scheduler: cosine
Batch size: 2 × 4 (grad accumulation) = total 8
Training steps: 688
Full config: TRAIN.md

Framework versions

PEFT 0.15.2
Transformers 4.52.3
PyTorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.2

Downloads last month: 8

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for demoversion/Llama-3.2-3B-Instruct-PEFT-code-generation

Base model

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

Adapter

(762)

this model

demoversion
/

Llama-3.2-3B-Instruct-PEFT-code-generation