Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,30 @@ Intuitively it seemed like LISA training should suit a MoE pretty well; though I
|
|
12 |
|
13 |
Interesting thing about this one is it looks like it wasn't converging at the end of one epoch. Still more to learn.
|
14 |
|
15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
[<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)
|
18 |
<details><summary>See axolotl config</summary>
|
|
|
12 |
|
13 |
Interesting thing about this one is it looks like it wasn't converging at the end of one epoch. Still more to learn.
|
14 |
|
15 |
+
Nous capabilities:
|
16 |
+
|
17 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
18 |
+
|-----------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
19 |
+
|[CosMoEAlpacaLisa-4x1b](https://huggingface.co/Lambent/CosMoEAlpacaLisa-4x1b)| 23.44| 48.13| 41.13| 29.95| 35.66|
|
20 |
+
|
21 |
+
Comparisons:
|
22 |
+
|
23 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
24 |
+
|---------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
25 |
+
|[CosMoE-AlpacaLight-v0.6](https://huggingface.co/Lambent/CosMoE-AlpacaLight-v0.6)| 23.3| 52.15| 38.57| 29.01| 35.76|
|
26 |
+
|
27 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
28 |
+
|-------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
29 |
+
|[CosmoAlpacaLisa-0.3-1b](https://huggingface.co/Lambent/CosmoAlpacaLisa-0.3-1b)| 23.79| 51.61| 40.25| 29.97| 36.41|
|
30 |
+
|
31 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
32 |
+
|-------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
33 |
+
|[CosmoAlpacaLight-1b](https://huggingface.co/Lambent/CosmoAlpacaLight-1b)| 24.28| 51.31| 40.33| 29.47| 36.35|
|
34 |
+
|
35 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
36 |
+
|---------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
37 |
+
|[cosmo-1b](https://huggingface.co/HuggingFaceTB/cosmo-1b)| 22.97| 52.01| 38.02| 28.73| 35.43|
|
38 |
+
|
39 |
|
40 |
[<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)
|
41 |
<details><summary>See axolotl config</summary>
|