|
--- |
|
license: apache-2.0 |
|
base_model: google/t5-efficient-mini-nl24 |
|
datasets: |
|
- Open-Orca/FLAN |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text2text-generation |
|
--- |
|
|
|
|
|
# t5e-mini-nl24-flan |
|
|
|
|
|
25k steps on FLAN as an initial test/validation that [code](https://github.com/pszemraj/nanoT5/tree/flan-dataset) works. Not practically useful. |
|
|
|
```py |
|
from transformers import pipeline |
|
|
|
pipe = pipeline( |
|
"text2text-generation", |
|
model="pszemraj/t5e-mini-nl24-flan", |
|
) |
|
res = pipe( |
|
"How can mirrors be real if our eyes aren't real?", |
|
top_k=4, |
|
penalty_alpha=0.6, |
|
max_new_tokens=128, |
|
) |
|
print(res[0]["generated_text"]) |
|
``` |
|
|
|
|
