|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- llama |
|
- trl |
|
- not-for-all-audiences |
|
- sft |
|
base_model: NousResearch/Meta-Llama-3-8B |
|
datasets: |
|
- PygmalionAI/PIPPA |
|
- databricks/databricks-dolly-15k |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# Uploaded model |
|
|
|
- **Developed by:** Abdulhanan2006 |
|
- **License:** apache-2.0 |
|
- **Finetuned from model :** NousResearch/Meta-Llama-3-8B |
|
- **A model that generates text Similar to Character Ai Bots (Unfiltered) has been trained for 32+ hrs** |
|
|
|
# Presets |
|
- Best Guess (Novel AI) |
|
- Story Writer |
|
(Context and Instruction Presets are given below) |
|
|
|
(# Llama 3 Preset will be better) |
|
Context: https://huggingface.co/Abdulhanan2006/WaifuAI-L3-8B-8k/blob/main/WaifuAI-L3%20(Context).json |
|
Instruct: https://huggingface.co/Abdulhanan2006/WaifuAI-L3-8B-8k/blob/main/WaifuAI-L3%20(Instruct).json |
|
|
|
# Quantized Model |
|
https://huggingface.co/Abdulhanan2006/WaifuAI-L3-8B-8k-gguf |
|
|
|
|
|
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) |
