README.md

---
license: mit
language:
- en
pipeline_tag: text-generation
tags:
- gguf
- llama.cpp
- qwen
- qwen2.5
- instruct
- lora
- roleplay
- holiday
- storytelling
- local-inference
- quantization
- ggml
- llm
---

# Easter Spirit 2B (GGUF)

[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
[![Format: GGUF](https://img.shields.io/badge/Format-GGUF-orange)](#quantized-files)
[![Runtime: llama.cpp](https://img.shields.io/badge/Runtime-llama.cpp-purple)](https://github.com/ggerganov/llama.cpp)
[![Base: Qwen2.5-2B-Instruct](https://img.shields.io/badge/Base-Qwen2.5--2B--Instruct-lightgrey)](#model-details)
[![Hugging Face](https://img.shields.io/badge/Hugging%20Face-Model-yellow)](https://huggingface.co/ghostai1/Easter-Spirit2b)
[![LinkedIn](https://img.shields.io/badge/LinkedIn-ccengineering-0A66C2?logo=linkedin&logoColor=white)](https://www.linkedin.com/in/ccengineering/)

**Easter Spirit 2B** is a compact seasonal model fine-tuned for **warm, cheerful, and family-friendly** text generation.  
This repository provides **GGUF** builds optimized for **local inference** using the **llama.cpp** ecosystem and compatible runtimes.

**Quick links**
- Model: https://huggingface.co/ghostai1/Easter-Spirit2b
- Runtime: https://github.com/ggerganov/llama.cpp
- Author (LinkedIn): https://www.linkedin.com/in/ccengineering/

---

## Overview

This is a **tone/personality-focused** model. It emphasizes warmth, friendliness, and seasonal flavor rather than deep reasoning or strict technical accuracy.

Recommended for:
- Creative writing and short stories
- Holiday / spring-themed roleplay
- Light conversational assistants
- Local demos and low-resource systems

Not optimized for:
- Complex reasoning
- Factual retrieval
- Long-horizon planning

---

## Model Details

- **Model name:** Easter Spirit 2B
- **Base model:** Qwen2.5-2B-Instruct
- **Fine-tuning:** LoRA (merged)
- **Parameters:** ~2B
- **Format:** GGUF (llama.cpp compatible)
- **Language:** English
- **License:** MIT (base model license applies)

---

## Quantized Files

All files are produced from the same merged model and differ only in quantization.

| File | Quantization | Approx. Size |
|---|---|---:|
| `release_v1.TQ1_0.gguf` | TQ1_0 | ~0.47 GB |
| `release_v1.Q2_K.gguf` | Q2_K | ~0.68 GB |
| `release_v1.Q3_K_S.gguf` | Q3_K_S | ~0.76 GB |
| `release_v1.Q3_K_M.gguf` | Q3_K_M | ~0.82 GB |
| `release_v1.Q4_K_S.gguf` | Q4_K_S | ~0.94 GB |
| `release_v1.Q4_K_M.gguf` | Q4_K_M | ~0.99 GB |
| `release_v1.Q5_K_S.gguf` | Q5_K_S | ~1.10 GB |
| `release_v1.Q5_K_M.gguf` | Q5_K_M | ~1.13 GB |
| `release_v1.Q6_K.gguf` | Q6_K | ~1.27 GB |
| `release_v1.Q8_0.gguf` | Q8_0 | ~1.65 GB |

### Recommendations

- **Default (balanced):** `Q4_K_M`
- **Higher quality:** `Q5_K_M`, `Q6_K`, `Q8_0`
- **Low RAM systems:** `Q3_K_M`, `Q2_K`
- **Ultra-low memory (experimental):** `TQ1_0`

---

## Usage (llama.cpp)

### CPU-only

```bash
./llama-cli \
  -m release_v1.Q4_K_M.gguf \
  -ngl 0 \
  -c 4096 \
  -p "Write a cozy springtime story inspired by Easter morning in a small town."