Commit
•
8a5c4ee
1
Parent(s):
f022183
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,44 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
-
-
|
| 5 |
---
|
| 6 |
-
|
| 7 |
-
This model uses [Tulpar v0 7b](https://huggingface.co/HyperbeeAI/Tulpar-7b-v0) as a base and merged with [LimaRP LLama2 7B Lora version of the day 07/23/2023](https://huggingface.co/lemonilia/limarp-llama2).
|
| 8 |
-
|
| 9 |
-
This merge of Lora with Model was done with this [script](https://github.com/zarakiquemparte/zaraki-tools/blob/main/apply-lora.py)
|
| 10 |
-
|
| 11 |
-
## Usage:
|
| 12 |
-
|
| 13 |
-
Since this is a merge between Tulpar and LimaRP, the following instruction formats should work:
|
| 14 |
-
|
| 15 |
-
Alpaca 2:
|
| 16 |
-
|
| 17 |
-
```
|
| 18 |
-
### Instruction:
|
| 19 |
-
<prompt>
|
| 20 |
-
|
| 21 |
-
### Response:
|
| 22 |
-
<leave a newline blank for model to respond>
|
| 23 |
-
```
|
| 24 |
-
|
| 25 |
-
LimaRP instruction format:
|
| 26 |
-
|
| 27 |
-
```
|
| 28 |
-
<<SYSTEM>>
|
| 29 |
-
<character card and system prompt>
|
| 30 |
-
|
| 31 |
-
<<USER>>
|
| 32 |
-
<prompt>
|
| 33 |
-
|
| 34 |
-
<<AIBOT>>
|
| 35 |
-
<leave a newline blank for model to respond>
|
| 36 |
-
```
|
| 37 |
-
|
| 38 |
-
## Bias, Risks, and Limitations
|
| 39 |
-
|
| 40 |
-
This model is not intended for supplying factual information or advice in any form
|
| 41 |
-
|
| 42 |
-
## Training Details
|
| 43 |
-
|
| 44 |
-
This model is merged and can be reproduced using the tools mentioned above. Please refer to all provided links for extra model-specific details.
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
+
- llama2
|
| 5 |
---
|
| 6 |
+
Quantized GGUF of [Tulpar LimaRP L2 7b](https://huggingface.co/zarakiquemparte/tulpar-limarp-l2-7b)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|