Matrix commited on
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Aya-Not-Using-Only-Test GGUF Quantized Models
|
| 2 |
+
|
| 3 |
+
## Technical Details
|
| 4 |
+
- **Quantization Tool:** llama.cpp
|
| 5 |
+
- **Version:** version: 5340 (15e6125a)
|
| 6 |
+
|
| 7 |
+
## Model Information
|
| 8 |
+
- **Base Model:** [matrixportal/Aya-Not-Using-Only-Test](https://huggingface.co/matrixportal/Aya-Not-Using-Only-Test)
|
| 9 |
+
- **Quantized by:** [matrixportal](https://huggingface.co/matrixportal)
|
| 10 |
+
|
| 11 |
+
## Available Files
|
| 12 |
+
| 🚀 Download | 🔢 Type | 📝 Description |
|
| 13 |
+
|------------|---------|---------------|
|
| 14 |
+
| [Download](https://huggingface.co/matrixportal/Aya-Not-Using-Only-Test-GGUF/resolve/main/aya-not-using-only-test.q4_k_m.gguf) | Q4 K M | 4-bit balanced (recommended default) |
|
| 15 |
+
|
| 16 |
+
💡 **Q4 K M** provides the best balance for most use cases
|