robinsyihab
commited on
Commit
•
7902bfa
1
Parent(s):
0e3ca9e
Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ license: apache-2.0
|
|
4 |
|
5 |
# Sidrap-7B-v2-GPTQ
|
6 |
|
7 |
-
Sidrap-7B-v2-GPTQ is an 8-bit quantized model of Sidrap-7B-v2, which is one of the best open model LLM bahasa Indonesia available today. This model has been quantized using
|
8 |
|
9 |
## Usage
|
10 |
|
|
|
4 |
|
5 |
# Sidrap-7B-v2-GPTQ
|
6 |
|
7 |
+
Sidrap-7B-v2-GPTQ is an 8-bit quantized model of Sidrap-7B-v2, which is one of the best open model LLM bahasa Indonesia available today. This model has been quantized using [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) to get smaller model that allows us to run in a lower resource environment with faster inference. The quantization uses random subset of original training data to "calibrate" the weights resulting in an optimally compact model with minimall loss in accuracy.
|
8 |
|
9 |
## Usage
|
10 |
|