Hugging Face's logo

allura-org
/
Teleut-7b-RP

Safetensors
qwen2
roleplay
conversational
Model card Files Community
Teleut-7b-RP / README.md
Fizzarolli's picture
Fizzarolli
Update README.md
dab3f7b verified
preview code
|
raw
history blame
1.23 kB
metadata
license: apache-2.0
base_model:
  - allura-org/Teleut-7b
tags:
  - roleplay
  - conversational

Teleut 7b RP

[cute boygirlthing pending]

A roleplay-focused LoRA finetune of Teleut 7b. Methodology and hyperparams inspired by SorcererLM and Slush.

Dataset

The worst mix of data you've ever seen. Like, seriously, you do not want to see the things that went into this model. It's bad.

Recommended Settings

Chat template: ChatML
Recommended samplers (not the be-all-end-all, try some on your own!):

  • Temp 1.03 / TopK 200 / MinP 0.05 / TopA 0.2
  • Temp 1.03 / TFS 0.75 / TopA 0.3

Hyperparams

General

  • Epochs = 2
  • LR = 6e-5
  • LR Scheduler = Cosine
  • Optimizer = Paged AdamW 8bit
  • Effective batch size = 12

LoRA

  • Rank = 16
  • Alpha = 32
  • Dropout = 0.25 (Inspiration: Slush)

Credits

Humongous thanks to the people who created the data. I would credit you all, but that would be cheating ;)
Big thanks to all Allura members, especially Toasty, for testing and emotional support ilya /platonic
NO thanks to Infermatic. They suck at hosting models