|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- ehartford/wizard_vicuna_70k_unfiltered |
|
--- |
|
|
|
# Overview |
|
Fine-tuned [OpenLLaMA-7B](https://huggingface.co/openlm-research/open_llama_7b) with an uncensored/unfiltered Wizard-Vicuna conversation dataset [ehartford/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered). |
|
Used QLoRA for fine-tuning. Trained for one epoch on a 24GB GPU (NVIDIA A10G) instance, took ~18 hours to train. |
|
|
|
# Training code |
|
Code used to train the model is available [here](https://github.com/georgesung/llm_qlora). |
|
|
|
# Demo |
|
For a Gradio chat application using this model, clone [this HuggingFace Space](https://huggingface.co/spaces/georgesung/open_llama_7b_qlora_uncensored_chat/tree/main) and run it on top of a GPU instance. |
|
The basic T4 GPU instance will work. |
|
|
|
# Blog post |
|
Since this was my first time fine-tuning an LLM, I also wrote an accompanying blog post about how I performed the training :) |
|
|
|
https://georgesung.github.io/ai/qlora-ift/ |
