Commit
•
1f46535
1
Parent(s):
6e5665b
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ The model is quantized version of the [google/flan-t5-small](https://huggingface
|
|
| 20 |
The model being quantized using [CTranslate2](https://opennmt.net/CTranslate2/) with the following command:
|
| 21 |
|
| 22 |
```
|
| 23 |
-
ct2-transformers-converter --model google/flan-t5-small --output_dir google/flan-t5-small-ct2 --quantization int8
|
| 24 |
```
|
| 25 |
|
| 26 |
If you want to perform the quantization yourself, you need to install the following dependencies:
|
|
|
|
| 20 |
The model being quantized using [CTranslate2](https://opennmt.net/CTranslate2/) with the following command:
|
| 21 |
|
| 22 |
```
|
| 23 |
+
ct2-transformers-converter --model google/flan-t5-small --output_dir google/flan-t5-small-ct2 --copy_files tokenizer.json tokenizer_config.json special_tokens_map.json spiece.model --quantization int8 --force
|
| 24 |
```
|
| 25 |
|
| 26 |
If you want to perform the quantization yourself, you need to install the following dependencies:
|