Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
base_model: HuggingFaceTB/cosmo-1b
|
4 |
tags:
|
5 |
- generated_from_trainer
|
@@ -11,6 +11,27 @@ model-index:
|
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
15 |
<details><summary>See axolotl config</summary>
|
16 |
|
|
|
1 |
---
|
2 |
+
license: cc
|
3 |
base_model: HuggingFaceTB/cosmo-1b
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
+
Trying out some LISA training.
|
15 |
+
This one used the same learning rate as the LORA training and only 4 layers each 10 steps.
|
16 |
+
Honestly these numbers are probably noise, with how close they are.
|
17 |
+
|
18 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
19 |
+
|-------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
20 |
+
|[CosmoAlpacaLisa-0.2-1b](https://huggingface.co/Lambent/CosmoAlpacaLisa-0.2-1b)| 23.81| 51.75| 39.31| 29.04| 35.98|
|
21 |
+
|
22 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
23 |
+
|-----------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
24 |
+
|[CosmoAlpacaLisa-1b](https://huggingface.co/Lambent/CosmoAlpacaLisa-1b)| 23.89| 51.93| 39.93| 28.68| 36.11|
|
25 |
+
|
26 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
27 |
+
|-------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
28 |
+
|[CosmoAlpacaLight-1b](https://huggingface.co/Lambent/CosmoAlpacaLight-1b)| 24.28| 51.31| 40.33| 29.47| 36.35|
|
29 |
+
|
30 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
31 |
+
|---------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
32 |
+
|[cosmo-1b](https://huggingface.co/HuggingFaceTB/cosmo-1b)| 22.97| 52.01| 38.02| 28.73| 35.43|
|
33 |
+
|
34 |
+
|
35 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
36 |
<details><summary>See axolotl config</summary>
|
37 |
|