Commit
•
a7ec7dc
1
Parent(s):
29ff7b3
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,41 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- InferenceIllusionist/Excalibur-7b
|
4 |
+
library_name: transformers
|
5 |
+
tags:
|
6 |
+
- finetune
|
7 |
+
- dpo
|
8 |
+
- chatml
|
9 |
+
- gguf
|
10 |
license: apache-2.0
|
11 |
+
datasets:
|
12 |
+
- Intel/orca_dpo_pairs
|
13 |
---
|
14 |
+
|
15 |
+
|
16 |
+
# Excalibur-7b-DPO-GGUF
|
17 |
+
|
18 |
+
<img src="https://i.imgur.com/pbPbqq0.jpeg" width="550"/>
|
19 |
+
|
20 |
+
An initial foray into the world of fine-tuning. The goal of this release was to amplify the quality of the original model's responses, in particular for vision use cases*
|
21 |
+
|
22 |
+
<b>FP16 available [here](https://huggingface.co/InferenceIllusionist/Excalibur-7b-DPO)</b>
|
23 |
+
|
24 |
+
## Notes & Methodology
|
25 |
+
* [Excalibur-7b](https://huggingface.co/InferenceIllusionist/Excalibur-7b) fine-tuned with Direct Preference Optimization (DPO) using Intel/orca_dpo_pairs
|
26 |
+
* This is a quick experiment to determine the impact of DPO finetuning on the original base model
|
27 |
+
* Ran for a little over an hour on a single A100
|
28 |
+
* Internal benchmarks showed improvement over base model, awaiting final results
|
29 |
+
* Precision: bfloat16
|
30 |
+
|
31 |
+
|
32 |
+
## Sample Question - Vision
|
33 |
+
<img src="https://i.imgur.com/7aRWtzU.jpeg" width="425"/>
|
34 |
+
|
35 |
+
<b>Requires additional [mistral-7b-mmproj-v1.5-Q4_1.gguf](https://huggingface.co/koboldcpp/mmproj/tree/main) file for vision functionality</b>
|
36 |
+
|
37 |
+
Select the gguf file of your choice in Kobold as usual, then make sure to choose the mmproj file above in the LLaVA mmproj field of the model submenu:
|
38 |
+
<img src="https://i.imgur.com/x8vqH29.png" width="425"/>
|
39 |
+
|
40 |
+
## Prompt Format
|
41 |
+
* For best results please use ChatML for the prompt format. Alpaca may also work.
|