34 lines
1.3 KiB
Markdown
34 lines
1.3 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
license: apache-2.0
|
|
tags:
|
|
- text-generation-inference
|
|
- transformers
|
|
- unsloth
|
|
- llama
|
|
- gguf
|
|
- trl
|
|
- sft
|
|
base_model: unsloth/tinyllama-bnb-4bit
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
**IA IA! A tiny Cthulhu cultist!**
|
|
This TinyLlama variant is fine tuned on Cthulhu Mythos, so you can have your very own cultist AI friend.
|
|
|
|
**5/3/24 Update:** The model was given a bit more training and several gguf files were uploaded.
|
|
|
|
This model was mainly created to test a cthulhu-fied data set. This tiny model is a proof of concept, before a larger model is trained on the full data set. At that point, I will also make the data set public.
|
|
|
|
The Cthulhu Mythos data set is based on alpaca-cleaned, except all the replies have been re-written to sound like they were given by a cultist of Cthulhu. Only a subset of the data (10k entries) was used to train the first iteration of this model
|
|
|
|
# Uploaded model
|
|
|
|
- **Developed by:** theprint
|
|
- **License:** apache-2.0
|
|
- **Finetuned from model :** unsloth/tinyllama-bnb-4bit
|
|
|
|
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |