Update README.md
Browse files
README.md
CHANGED
|
@@ -18,8 +18,11 @@ license: apache-2.0
|
|
| 18 |
|
| 19 |
This is a version of `hivemind/gpt-j-6B-8bit` fine-tuned on the [Wizard of Wikipedia](https://arxiv.org/abs/1811.01241) dataset for 10k steps (_just under an epoch_) on an A100. it can be used as a chatbot. It is designed to be used with [ai-msgbot](https://github.com/pszemraj/ai-msgbot) to take advantage of the prompt engineering.
|
| 20 |
|
|
|
|
| 21 |
|
| 22 |
-
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Training
|
| 25 |
|
|
|
|
| 18 |
|
| 19 |
This is a version of `hivemind/gpt-j-6B-8bit` fine-tuned on the [Wizard of Wikipedia](https://arxiv.org/abs/1811.01241) dataset for 10k steps (_just under an epoch_) on an A100. it can be used as a chatbot. It is designed to be used with [ai-msgbot](https://github.com/pszemraj/ai-msgbot) to take advantage of the prompt engineering.
|
| 20 |
|
| 21 |
+
## Usage
|
| 22 |
|
| 23 |
+
_**NOTE: this needs to be loaded via the special patching technique** outlined in the hivemind model card (as with all 8bit models)_
|
| 24 |
+
|
| 25 |
+
Examples of how to load the model correctly are already in place in the notebook linked above. A `.py` of said notebook was uploaded to the repo for reference - [link here](https://huggingface.co/ethzanalytics/gpt-j-8bit-KILT_WoW_10k_steps/commit/2e9abb9880da50ca7f58ca42c39728bd1f9c66cb)
|
| 26 |
|
| 27 |
## Training
|
| 28 |
|