Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
{}
|
3 |
+
---
|
4 |
+
|
5 |
+
---
|
6 |
+
language: en
|
7 |
+
tags:
|
8 |
+
- torchtune
|
9 |
+
---
|
10 |
+
|
11 |
+
# My Torchtune Model
|
12 |
+
|
13 |
+
This model is a finetuned version of [None](https://huggingface.co/None)
|
14 |
+
|
15 |
+
# Model description
|
16 |
+
|
17 |
+
More information needed
|
18 |
+
|
19 |
+
# Training and evaluation results
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
# Training procedure
|
24 |
+
|
25 |
+
This model was trained using the [torchtune](https://github.com/pytorch/torchtune) library using the following command:
|
26 |
+
|
27 |
+
```bash
|
28 |
+
/Users/salmanmohammadi/projects/torchtune/recipes/lora_finetune_single_device.py --config /Users/salmanmohammadi/projects/torchtune/recipes/configs/gemma/2B_lora_single_device.yaml \
|
29 |
+
device=mps \
|
30 |
+
epochs=1 \
|
31 |
+
max_steps_per_epoch=10
|
32 |
+
```
|
33 |
+
|
34 |
+
# Framework versions
|
35 |
+
|
36 |
+
- torchtune 0.0.0
|
37 |
+
- torchao 0.5.0
|
38 |
+
- datasets 2.20.0
|
39 |
+
- sentencepiece 0.2.0
|
40 |
+
|
41 |
+
|