Downloads · 30 days
4
10% of all-time downloads
LoneStriker/Thespis-13b-Alpha-v0.7-8.0bpw-h8-exl2
Thespis-13b-Alpha-v0.7-8.0bpw-h8-exl2 is a text generation model from LoneStriker. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Downloads · 30 days
4
10% of all-time downloads
All-time downloads
40
Public
Repo size
13.2 GB
Likes
0
Public
Click a slice to open those files.
.safetensors13.2 GB · 100%
From the Hugging Face model README

This is a version of Thespis which includes more than the usual amount of Assistant responses in the training data. Its good for acting as an assistant with personality. It may be ok for RP, feel free to experiment. It was also trained on DaringFortitude as opposed to the base Llama2 13b.
This model works best with internet style RP using standard markup with asterisks surrounding actions and no quotes around dialogue. Currently in the middle of adding new features and working on making sure initial responses are strong.
It uses a 40/60 Split of Assistant and RP data, and includes items from the below datasets:
As a result of adding this additional Assistant data, the model shows greatly improved instruction following and coherence during multiturn chats.
Works with standard chat format for Ooba or SillyTavern.
{System Prompt}
Username: {Input}
BotName: {Response}
Username: {Input}
BotName: {Response}


You can either bake usernames into the prompt directly for ease of use or programatically add them if running through the API to use as a chatbot.
User string: ( Leave empty if populating username into prompt through a script. Put in your username if its a 1 on 1 convo.) Ex. "DiscordUser1: "
Bot String: ( The bots name, followed by a colon and a space.) Ex. "Mayo: "
Context: ( Your bots system prompt, follow by a newline. )
<|user|><|user-message|>\n<|bot|><|bot-message|>\n