ajibawa-2023
commited on
Commit
•
46063d0
1
Parent(s):
d2e41f3
Update README.md
Browse files
README.md
CHANGED
@@ -19,13 +19,13 @@ tags:
|
|
19 |
**Code-Jamba-v0.1**
|
20 |
|
21 |
This model is trained upon my dataset [Code-290k-ShareGPT](https://huggingface.co/datasets/ajibawa-2023/Code-290k-ShareGPT) and [Code-Feedback](https://huggingface.co/datasets/m-a-p/Code-Feedback). It is finetuned on Jamba-v0.1 .
|
22 |
-
|
23 |
This model will also generate detailed explanation/logic behind each code.
|
24 |
This model uses ChatML prompt format.
|
25 |
|
26 |
**Training**
|
27 |
|
28 |
-
Entire dataset was trained on 2 x H100 94GB. For 3 epoch, training took 162 hours
|
29 |
|
30 |
This is a qlora model. Links for quantized models will be updated very soon.
|
31 |
|
|
|
19 |
**Code-Jamba-v0.1**
|
20 |
|
21 |
This model is trained upon my dataset [Code-290k-ShareGPT](https://huggingface.co/datasets/ajibawa-2023/Code-290k-ShareGPT) and [Code-Feedback](https://huggingface.co/datasets/m-a-p/Code-Feedback). It is finetuned on Jamba-v0.1 .
|
22 |
+
It is very very good in Code generation in various languages such as **Python, Java, JavaScript, GO, C++, Rust, Ruby, Sql, MySql, R, Julia, Haskell**, etc..
|
23 |
This model will also generate detailed explanation/logic behind each code.
|
24 |
This model uses ChatML prompt format.
|
25 |
|
26 |
**Training**
|
27 |
|
28 |
+
Entire dataset was trained on **2 x H100** 94GB. For 3 epoch, training took **162 hours**. Axolotl along with DeepSpeed codebase was used for training purpose. This was trained on Jamba-v0.1 by AI21Labs.
|
29 |
|
30 |
This is a qlora model. Links for quantized models will be updated very soon.
|
31 |
|