Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


MFANN3bv0.17 - bnb 4bits
- Model creator: https://huggingface.co/netcat420/
- Original model: https://huggingface.co/netcat420/MFANN3bv0.17/




Original model description:
---
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)