Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,49 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- zho
|
| 5 |
+
- eng
|
| 6 |
+
- fra
|
| 7 |
+
- spa
|
| 8 |
+
- por
|
| 9 |
+
- deu
|
| 10 |
+
- ita
|
| 11 |
+
- rus
|
| 12 |
+
- jpn
|
| 13 |
+
- kor
|
| 14 |
+
- vie
|
| 15 |
+
- tha
|
| 16 |
+
- ara
|
| 17 |
+
pipeline_tag: text-generation
|
| 18 |
+
datasets:
|
| 19 |
+
- DiamondGotCat/Zeta-2-Dataset
|
| 20 |
+
---
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
# Challenging the limit of 464M params: Zeta 4
|
| 25 |
+
|
| 26 |
+
## Prompt Template
|
| 27 |
+
```
|
| 28 |
+
{{ if .System }}{{ .System }}{{ end }}
|
| 29 |
+
{{ if .Prompt }}<USER>{{ .Prompt }}</USER>{{ end }}
|
| 30 |
+
<ASSISTANT>
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
+
## Stop Token
|
| 34 |
+
`</ASSISTANT>`
|
| 35 |
+
|
| 36 |
+
## Computer Spec
|
| 37 |
+
|
| 38 |
+
**Machine:** *RunPod VM(GPU, NVIDIA A100 PCIe)*
|
| 39 |
+
|
| 40 |
+
## Dataset
|
| 41 |
+
Details of the dataset used can be found [here](https://github.com/DiamondGotCat/Zeta-Dataset/releases/tag/zeta-2)
|
| 42 |
+
|
| 43 |
+
## Links
|
| 44 |
+
GitHub: [Zeta](https://github.com/Zeta-LLM/Zeta/)
|
| 45 |
+
|
| 46 |
+
---
|
| 47 |
+
|
| 48 |
+
Zeta is just a small SLM.
|
| 49 |
+
But don't forget that it has big dreams inside.
|