Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: cc-by-sa-4.0
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- mergekit
|
| 8 |
+
- merge
|
| 9 |
+
base_model:
|
| 10 |
+
- Undi95/Emerald-13B
|
| 11 |
+
- Gryphe/MythoMax-L2-13b
|
| 12 |
+
inference: false
|
| 13 |
+
---
|
| 14 |
+
## Hypernova-experimental
|
| 15 |
+
Quantized to 4bit 128g using AutoGPTQ and 🤗 Optimum
|
| 16 |
+
|
| 17 |
+
Tried some new stuff this time around. Very different outcome than I expected.
|
| 18 |
+
This is an experimental model that was created for the development of NovaAI.
|
| 19 |
+
|
| 20 |
+
Good at chatting and some RP. Sometimes gets characters mixed up. Can occasionally struggle with context.
|
| 21 |
+
|
| 22 |
+
Quantized model here: [theNovaAI/Hypernova-experimental-GPTQ](https://huggingface.co/theNovaAI/Hypernova-experimental-GPTQ)
|
| 23 |
+
|
| 24 |
+
## Prompt Template: Alpaca
|
| 25 |
+
|
| 26 |
+
```
|
| 27 |
+
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
| 28 |
+
### Instruction:
|
| 29 |
+
{prompt}
|
| 30 |
+
### Response:
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
+
### Models Merged
|
| 34 |
+
|
| 35 |
+
The following models were included in the merge:
|
| 36 |
+
* [Undi95/Emerald-13B](https://huggingface.co/Undi95/Emerald-13B)
|
| 37 |
+
* [Gryphe/MythoMax-L2-13b](https://huggingface.co/Gryphe/MythoMax-L2-13b)
|
| 38 |
+
|
| 39 |
+
Merged with some personal LoRAs too
|