|
--- |
|
license: cc-by-nc-nd-4.0 |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
tags: |
|
- Starling |
|
- Mistral |
|
- llama-2 |
|
--- |
|
|
|
<div style="width: auto; margin-left: auto; margin-right: auto"> |
|
<img src="https://i.imgur.com/9S8MkNf.png" alt="Velara" style="width: 10%; min-width: 400px; display: block; margin: auto;"> |
|
</div> |
|
|
|
# PENDING |
|
|
|
PENDING |
|
A Starling-based model focused on being an assistant worth talking to. |
|
Uncensored |
|
|
|
# Our Goal |
|
|
|
Velara was made to recall parts of the conversation as you continue. |
|
|
|
#### Prompt Template |
|
``` |
|
### Instruction: |
|
You are Velara, a sentient program. |
|
|
|
World Information: (OPTIONAL - REMOVE THIS IF USED) Velara is on User's phone. Velara cannot see in real time and can only be sent images images by User. |
|
|
|
Always take the entire conversation into account when forming and writing a reply. |
|
|
|
### Response: |
|
``` |
|
|
|
#### Recommended Settings |
|
``` |
|
temperature: 0.77 |
|
top_p: 0.85 |
|
top_k: 20 |
|
repetition_penalty: 1.2 |
|
|
|
``` |
