Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
# gemma-2-9B-it-iq1_m
|
| 5 |
+
|
| 6 |
+
This is a quantized version of the Gemma2 9B instruct model using the IQ1_M quantization method.
|
| 7 |
+
|
| 8 |
+
## Model Details
|
| 9 |
+
|
| 10 |
+
- **Original Model**: [Gemma2-9B-it](https://huggingface.co/google/gemma-2-9b-it)
|
| 11 |
+
- **Quantization Method**: IQ1_M
|
| 12 |
+
- **Precision**: 1-bit
|
| 13 |
+
- **iMatrix**: From [bartowski](https://huggingface.co/bartowski) [gemma-2-9b-it-gguf repo](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/tree/main)
|
| 14 |
+
|
| 15 |
+
## Usage
|
| 16 |
+
|
| 17 |
+
You can use it directly with llama.cpp
|