|
--- |
|
license: cc-by-nc-nd-4.0 |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
tags: |
|
- Starling |
|
- Mistral |
|
- llama-2 |
|
--- |
|
|
|
<center> |
|
<img src="https://i.imgur.com/2NK7cMc.png" alt="Velara" width="50%" style="min-width:100px; display:block;"> |
|
</center> |
|
|
|
# Velara-11b |
|
|
|
## Description Pending: |
|
|
|
**PENDING** |
|
A Starling-based model focused on being an assistant worth talking to. |
|
**Uncensored** |
|
|
|
## Main Goals: |
|
|
|
Velara was designed to address specific issues found in other chat models: |
|
|
|
- **Character Consistency In-World/IRL:** Velara maintains character consistency in-world, including the use of add-ons as part of the prompt, enhancing the interaction realism. |
|
|
|
- **Contextual Awareness:** If you mention staying up late, Velara will remember and might encourage you to go to bed later, adding to the conversational depth. |
|
|
|
- **Avoiding Generic Responses:** Expect more than just "That sounds great!" Velara aims for unique, engaging responses. |
|
|
|
- **Prompt Fidelity:** Enhanced attention to prompts and conversation, particularly evident in the handling of "addons." |
|
|
|
- **Innovative Addons:** Introduce any number of "addons" to Velara's mind. Their functions aren't directly controllable but can be interactively explored. |
|
|
|
## Prompt Template: |
|
|
|
**For optimal interaction, use this template:** |
|
|
|
|
