temp readme
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: unknown
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: unknown
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- zh
|
| 6 |
+
library_name: CTranslate2
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
tags:
|
| 9 |
+
- facebook
|
| 10 |
+
- meta
|
| 11 |
+
- llama
|
| 12 |
+
- llama-3
|
| 13 |
+
- kaltcit
|
| 14 |
+
- ct2
|
| 15 |
+
- quantized model
|
| 16 |
+
- int8
|
| 17 |
+
base_model: turboderp/unknown
|
| 18 |
+
---
|
| 19 |
+
# CTranslate2 int8 version of turbcat
|
| 20 |
+
|
| 21 |
+
This is a int8_float16 quantization of [turbcat](not released yet)\
|
| 22 |
+
See more on CTranslate2: [Docs](https://opennmt.net/CTranslate2/index.html) | [Github](https://github.com/OpenNMT/CTranslate2)
|
| 23 |
+
|
| 24 |
+
This model was converted to ct2 format using the following commnd:
|
| 25 |
+
```
|
| 26 |
+
ct2-transformers-converter --model kat_turbcat --output_dir turbcat-ct2 --quantization int8_bfloat16 --low_cpu_mem_usage
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
***no converstion needed using the model from this repository as it is already in ct2 format.***
|