Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,7 @@ Fine-tuned [Llama-2 70B](https://huggingface.co/TheBloke/Llama-2-70B-fp16) with
|
|
| 14 |
[QLoRA](https://arxiv.org/abs/2305.14314) was used for fine-tuning. The model was trained for three epochs on a single NVIDIA A100 80GB GPU instance, taking ~1 week to train.
|
| 15 |
|
| 16 |
Please note that LLama 2 Base model has its inherit biases.
|
|
|
|
| 17 |
|
| 18 |
Special thanks to [George Sung](https://huggingface.co/georgesung) for creating [llama2_7b_chat_uncensored](https://huggingface.co/georgesung/llama2_7b_chat_uncensored), and to [Eric Hartford](https://huggingface.co/ehartford/) for creating [ehartford/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered)
|
| 19 |
|
|
|
|
| 14 |
[QLoRA](https://arxiv.org/abs/2305.14314) was used for fine-tuning. The model was trained for three epochs on a single NVIDIA A100 80GB GPU instance, taking ~1 week to train.
|
| 15 |
|
| 16 |
Please note that LLama 2 Base model has its inherit biases.
|
| 17 |
+
Uncensored refers to the [ehartford/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered) dataset.
|
| 18 |
|
| 19 |
Special thanks to [George Sung](https://huggingface.co/georgesung) for creating [llama2_7b_chat_uncensored](https://huggingface.co/georgesung/llama2_7b_chat_uncensored), and to [Eric Hartford](https://huggingface.co/ehartford/) for creating [ehartford/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered)
|
| 20 |
|