|
--- |
|
license: other |
|
license_name: xt-aurora-license |
|
license_link: LICENSE |
|
language: |
|
- en |
|
tags: |
|
- conversational |
|
- chat |
|
- rp |
|
- roleplay |
|
- friend |
|
- slm |
|
- small |
|
- slim |
|
- slender |
|
- general |
|
- creative |
|
|
|
co2_eq_emissions: |
|
emissions: 200 |
|
training_type: "fine-tuning" |
|
hardware_used: "1 GTX1060-3GB, AMD Radeon(TM) Graphics & AMD Ryzen 5 5600G[4.4GHz OC]" |
|
--- |
|
|
|
NOTE / ANNOUNCEMENT: |
|
We've jumped from V0.5 to this version, V1.0, this is the last version of the series. |
|
We're sad to announce the end of XT_AURORA, our first SLM series, due to no community activity. |
|
We, XeTute, have put in a lot of effort and countless nights to improve our models, but given on how much time, passion and effort we've put in, we got nothing back from the community. |
|
Thank you for so many downloads on this series of SLMs. We'll continue to update model cards and chat templates. |
|
Thank you for being part of our journey. |
|
|
|
About this model: |
|
This model, XT_AURORA, is by us, XeTute. The model was finetuned ontop of the previos beta-verion[XT_AURORA-OpenBeta-V0.5-GGUF]. |
|
This version[V1.0] achieves better general performance, it outperforms every previos model[V0.1 - V0.5]. |
|
|
|
About XT_AURORA: |
|
XT_AURORA is a series of SLMs[Slender Language Models], which all aim to provide a friendly, human-like conversation. |
|
The serie is limited by its size[about 1.1B Params], but we still try to get the best possible output. |
|
The context-length is very stable till 2048 tokens, after that limit, it will perform only slightly better than V0.5. |
|
Tt can be upscaled using rope, with the cost being slightly less logic. |
|
|
|
About this version[V1.0]: |
|
* High quality output[sometimes outperforms 3B models in HumanEval], as long as the context size is under 2049 Tokens. |
|
* We provide a system prompt[Files and Versions --> chat_template]. The SLM was partly trained using that template, so the output is better if you use the prompt at start. |
|
* AURORA expects the chat template to be Vicuna[{{user}}: {some input}\nAURORA: {some output}\n{{user}}]. The model will only work correctly with this format. |
|
* Recommended temperature is from 0.4 to 0.75. |
|
* Improved chat quality in general emotional / unemotional chat, logical & illogical roleplaying, etc. |
|
|
|
All in one, AURORA's aim is to provide a digital friend, which is also accessible to humans with low-end devices. |
|
|
|
Using KoboldCPP, we got the model running[using termux] on a POCO X5 Pro 5G[CPU only, Octa Core]. |
|
We saw ~5 Tokens generation per second, ~15 Tokens processing per second. [In Energy Saver mode] |
|
|
|
Support us: |
|
X: <https://www.x.com/XeTute> |
|
GitHub: <https://www.github.com/N0CTRON/> |
|
Subdomain on Neocities: <https://xetute.neocities.org/> |
|
|
|
We wish you a friendly chat with AURORA. |
