106 lines
3.0 KiB
Markdown
106 lines
3.0 KiB
Markdown
|
---
|
||
|
|
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)
|
||
|
|
[](#quantized-files)
|
||
|
|
[](https://github.com/ggerganov/llama.cpp)
|
||
|
|
[](#model-details)
|
||
|
|
[](https://huggingface.co/ghostai1/Easter-Spirit2b)
|
||
|
|
[](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."
|