Commit
•
acb2b95
1
Parent(s):
e7ce6ac
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
# Fast-Inference with Ctranslate2
|
| 5 |
Speedup inference by 2x-8x using int8 inference in C++
|
|
@@ -18,7 +21,7 @@ Checkpoint compatible to [ctranslate2](https://github.com/OpenNMT/CTranslate2) a
|
|
| 18 |
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
|
| 19 |
|
| 20 |
model_name = "michaelfeil/ct2fast-flan-alpaca-xl"
|
| 21 |
-
model =
|
| 22 |
# load in int8 on CUDA
|
| 23 |
model_name_or_path=model_name,
|
| 24 |
device="cuda",
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- ctranslate2
|
| 5 |
+
- t5
|
| 6 |
---
|
| 7 |
# Fast-Inference with Ctranslate2
|
| 8 |
Speedup inference by 2x-8x using int8 inference in C++
|
|
|
|
| 21 |
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
|
| 22 |
|
| 23 |
model_name = "michaelfeil/ct2fast-flan-alpaca-xl"
|
| 24 |
+
model = TranslatorCT2fromHfHub(
|
| 25 |
# load in int8 on CUDA
|
| 26 |
model_name_or_path=model_name,
|
| 27 |
device="cuda",
|