Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
---
|
8 |
+
|
9 |
+
# Introduction
|
10 |
+
This model vistagi/Mixtral-8x7b-v0.1-sft is trained with Ultrachat-200K dataset through supervised finetuning using Mixtral-8x7b-v0.1 as the baseline model. The training is done with bfloat16 precision using LoRA.
|
11 |
+
|
12 |
+
## Details
|
13 |
+
Used Librarys
|
14 |
+
- torch
|
15 |
+
- deepspeed
|
16 |
+
- pytorch lightning
|
17 |
+
- transformers
|
18 |
+
- peft
|