---
library_name: transformers
license: mit
datasets:
- netcat420/MFANN
language:
- en
pipeline_tag: text-generation
---

Prompt template for GPT4All:

```
<|endoftext|>Instruct: %1<|endoftext|>
<|endoftext|>Output: %2<|endoftext|>
```


record low training loss on netcat420/MFANN for the 2.78b model!

(0.538)

previous record: (0.632)


![image/png](https://cdn-uploads.huggingface.co/production/uploads/6435f27b2d0ed796668ffd8b/Qe37qIY1nmtHxCZTYXL2P.png)