Commit ·
4312921
1
Parent(s): 2d481d1
Update README.md
Browse files
README.md
CHANGED
|
@@ -59,7 +59,7 @@ Here, we also apply [LoRA (Low Rank Adpatars](https://arxiv.org/abs/2106.09685)
|
|
| 59 |
|
| 60 |
### How to use
|
| 61 |
|
| 62 |
-
This model can be used by adapting Bloom original implementation:
|
| 63 |
|
| 64 |
```python
|
| 65 |
import transformers
|
|
@@ -216,7 +216,11 @@ tokenizer = BloomTokenizerFast.from_pretrained('joaoalvarenga/bloom-8bit')
|
|
| 216 |
|
| 217 |
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')
|
| 218 |
out = model.generate(**prompt, min_length=10, do_sample=True)
|
| 219 |
-
tokenizer.decode(out[0])
|
|
|
|
|
|
|
|
|
|
|
|
|
| 220 |
|
| 221 |
|
| 222 |
|
|
|
|
| 59 |
|
| 60 |
### How to use
|
| 61 |
|
| 62 |
+
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):
|
| 63 |
|
| 64 |
```python
|
| 65 |
import transformers
|
|
|
|
| 216 |
|
| 217 |
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')
|
| 218 |
out = model.generate(**prompt, min_length=10, do_sample=True)
|
| 219 |
+
tokenizer.decode(out[0])
|
| 220 |
+
```
|
| 221 |
+
|
| 222 |
+
|
| 223 |
+
|
| 224 |
|
| 225 |
|
| 226 |
|