Update README.md

README.md

@@ -59,7 +59,7 @@ Here, we also apply [LoRA (Low Rank Adpatars](https://arxiv.org/abs/2106.09685)
 
 ### How to use
 
-This model can be used by adapting Bloom original implementation:
+This model can be used by adapting Bloom original implementation. This is an adaptation from [Hivemind's GPT-J 8-bit](https://nbviewer.org/urls/huggingface.co/hivemind/gpt-j-6B-8bit/raw/main/convert-gpt-j.ipynb):
 
 ```python
 import transformers
@@ -216,7 +216,11 @@ tokenizer = BloomTokenizerFast.from_pretrained('joaoalvarenga/bloom-8bit')
 
 prompt = tokenizer("Given a table named salaries and columns id, created_at, salary, age. Creates a SQL to answer What is the average salary for 22 years old:", return_tensors='pt')
 out = model.generate(**prompt, min_length=10, do_sample=True)
-tokenizer.decode(out[0])```
+tokenizer.decode(out[0])
+```
+
+
+