Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- text-generation
|
| 4 |
+
- 8bit
|
| 5 |
+
- 8-bit
|
| 6 |
+
- quantization
|
| 7 |
+
- compression
|
| 8 |
+
inference: False
|
| 9 |
+
license: apache-2.0
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# ethzanalytics/gpt-j-8bit-daily_dialogues_1E
|
| 13 |
+
|
| 14 |
+
This is a version of `hivemind/gpt-j-6B-8bit` fine-tuned on the Wizard of Wikipedia dataset for 10k steps on an A100. it can be used as a chatbot.
|
| 15 |
+
|
| 16 |
+
_NOTE: this needs to be loaded via the special patching technique outlined in the hivemind model card (as with all 8bit models)_
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
TODO: rest of README
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
---
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
[original demo link](https://colab.research.google.com/gist/pszemraj/76c0a80c9eacfb2c31e21c4cceb344a0/ai-msgbot-gpt-j-6b-8bit-chatbot-demo.ipynb)
|
| 26 |
+
|