Anthonyg5005
commited on
Commit
•
0fb5ca8
1
Parent(s):
9eb7400
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
library_name: CTranslate2
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
tags:
|
8 |
+
- facebook
|
9 |
+
- meta
|
10 |
+
- llama
|
11 |
+
- llama-3
|
12 |
+
- ct2
|
13 |
+
- quantized model
|
14 |
+
- int8
|
15 |
+
---
|
16 |
+
# CTranslate2 int8 version of L3-8B-Stheno-v3.1
|
17 |
+
|
18 |
+
This is a int8_float16 quantization of [L3-8B-Stheno-v3.1](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.1)\
|
19 |
+
See more on CTranslate2: [Docs](https://opennmt.net/CTranslate2/index.html) | [Github](https://github.com/OpenNMT/CTranslate2)
|
20 |
+
|
21 |
+
This model was converted to ct2 format using the following commnd:
|
22 |
+
```
|
23 |
+
ct2-transformers-converter --model Sao10K/L3-8B-Stheno-v3.1 --output_dir L3-8B-Stheno-v3.1-ct2 --quantization int8_bfloat16 --low_cpu_mem_usage
|
24 |
+
```
|
25 |
+
|
26 |
+
***no converstion needed using the model from this repository as it is already in ct2 format.***
|