初始化项目,由ModelHub XC社区提供模型
Model: theprint/TiTan-Gemma3-0.27B-GGUF Source: Original Platform
This commit is contained in:
79
README.md
Normal file
79
README.md
Normal file
@@ -0,0 +1,79 @@
|
||||
---
|
||||
base_model: google/gemma-3-270m-it
|
||||
library_name: gguf
|
||||
pipeline_tag: text-generation
|
||||
language: en
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- gguf
|
||||
- quantized
|
||||
- llama.cpp
|
||||
- titan-gemma3-0.27b
|
||||
model_type: llama
|
||||
quantized_by: theprint
|
||||
---
|
||||
# TiTan-Gemma3-0.27B - GGUF Quantized
|
||||
|
||||
Quantized GGUF versions of [TiTan-Gemma3-0.27B](https://huggingface.co/theprint/TiTan-Gemma3-0.27B) for use with llama.cpp and other GGUF-compatible inference engines.
|
||||
|
||||
## Original Model
|
||||
|
||||
- **Base model:** [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it)
|
||||
- **Fine-tuned model:** [theprint/TiTan-Gemma3-0.27B](https://huggingface.co/theprint/TiTan-Gemma3-0.27B)
|
||||
- **Quantized by:** theprint
|
||||
|
||||
## Available Quantizations
|
||||
|
||||
- `TiTan-Gemma3-0.27B-f16.gguf` (837.7 MB) - 16-bit float (original precision, largest file)
|
||||
- `TiTan-Gemma3-0.27B-q3_k_m.gguf` (320.8 MB) - 3-bit quantization (medium quality)
|
||||
- `TiTan-Gemma3-0.27B-q4_k_m.gguf` (351.4 MB) - 4-bit quantization (medium, recommended for most use cases)
|
||||
- `TiTan-Gemma3-0.27B-q5_k_m.gguf` (368.0 MB) - 5-bit quantization (medium, good quality)
|
||||
- `TiTan-Gemma3-0.27B-q6_k.gguf` (439.9 MB) - 6-bit quantization (high quality)
|
||||
- `TiTan-Gemma3-0.27B-q8_0.gguf` (448.0 MB) - 8-bit quantization (very high quality)
|
||||
|
||||
## Usage
|
||||
|
||||
### With llama.cpp
|
||||
|
||||
```bash
|
||||
# Download recommended quantization
|
||||
wget https://huggingface.co/theprint/TiTan-Gemma3-0.27B-GGUF/resolve/main/TiTan-Gemma3-0.27B-q4_k_m.gguf
|
||||
|
||||
# Run inference
|
||||
./llama.cpp/main -m TiTan-Gemma3-0.27B-q4_k_m.gguf \
|
||||
-p "Your prompt here" \
|
||||
-n 256 \
|
||||
--temp 0.7 \
|
||||
--top-p 0.9
|
||||
```
|
||||
|
||||
### With other GGUF tools
|
||||
|
||||
These files are compatible with:
|
||||
- [llama.cpp](https://github.com/ggerganov/llama.cpp)
|
||||
- [Ollama](https://ollama.ai/) (import as custom model)
|
||||
- [KoboldCpp](https://github.com/LostRuins/koboldcpp)
|
||||
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
|
||||
|
||||
## Quantization Info
|
||||
|
||||
**Recommended:** `q4_k_m` provides the best balance of size, speed, and quality for most use cases.
|
||||
|
||||
**For maximum quality:** Use `q8_0` or `f16`
|
||||
**For maximum speed/smallest size:** Use `q3_k_m` or `q4_k_s`
|
||||
|
||||
## License
|
||||
|
||||
apache-2.0
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@misc{titan_gemma3_0.27b_gguf,
|
||||
title={TiTan-Gemma3-0.27B GGUF Quantized Models},
|
||||
author={theprint},
|
||||
year={2025},
|
||||
publisher={Hugging Face},
|
||||
url={https://huggingface.co/theprint/TiTan-Gemma3-0.27B-GGUF}
|
||||
}
|
||||
```
|
||||
Reference in New Issue
Block a user