Commit
•
d5f7662
1
Parent(s):
735d4d9
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,11 @@ datasets:
|
|
| 4 |
- ehartford/wizard_vicuna_70k_unfiltered
|
| 5 |
---
|
| 6 |
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- ehartford/wizard_vicuna_70k_unfiltered
|
| 5 |
---
|
| 6 |
|
| 7 |
+
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).
|
| 8 |
+
Used QLoRA for fine-tuning. Trained for one epoch on a 24GB GPU (NVIDIA A10G) instance, took ~18 hours to train.
|
| 9 |
+
|
| 10 |
+
Code used to train the model is available [here](https://github.com/georgesung/llm_qlora).
|
| 11 |
+
|
| 12 |
+
Since this was my first time fine-tuning an LLM, I also wrote an accompanying blog post about how I performed the training :)
|
| 13 |
+
|
| 14 |
+
https://georgesung.github.io/ai/qlora-ift/
|