aashish1904
commited on
Commit
•
cea4878
1
Parent(s):
fb3c16e
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
|
4 |
+
library_name: transformers
|
5 |
+
base_model:
|
6 |
+
- meta-llama/Meta-Llama-3.1-8B-Instruct
|
7 |
+
datasets:
|
8 |
+
- jondurbin/airoboros-3.2
|
9 |
+
license: llama3
|
10 |
+
|
11 |
+
---
|
12 |
+
|
13 |
+
![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)
|
14 |
+
|
15 |
+
# QuantFactory/llama3.1-airoboros3.2-QDT-8B-GGUF
|
16 |
+
This is quantized version of [nbeerbower/llama3.1-airoboros3.2-QDT-8B](https://huggingface.co/nbeerbower/llama3.1-airoboros3.2-QDT-8B) created using llama.cpp
|
17 |
+
|
18 |
+
# Original Model Card
|
19 |
+
|
20 |
+
|
21 |
+
# llama3.1-airoboros3.2-QDT-8B
|
22 |
+
|
23 |
+
[meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) finetuned on [jondurbin/airoboros-3.2](https://huggingface.co/datasets/jondurbin/airoboros-3.2).
|
24 |
+
|
25 |
+
Llama 3 Instruct was used as the chat template.
|
26 |
+
|
27 |
+
### Method
|
28 |
+
|
29 |
+
Finetuned using a Google Colab A100 for 1 epoch. Only 25% of the data was used for training due to limited resources, hence QDT (Quarter Data Test).
|
30 |
+
|
31 |
+
[Based on mlabonne's SFT notebook.](https://colab.research.google.com/drive/1o_w0KastmEJNVwT5GoqMCciH-18ca5WS?usp=sharing)
|