Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -47,7 +47,13 @@ demo = gr.Interface(
|
|
47 |
],
|
48 |
outputs=gr.Textbox(label="Generated Completion", lines=4),
|
49 |
title="LLaMA Text Completion",
|
50 |
-
description=
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
examples=[
|
52 |
["Once upon a time in a magical forest", 0.7, 50],
|
53 |
["The recipe for making the perfect chocolate cake requires", 0.7, 50],
|
|
|
47 |
],
|
48 |
outputs=gr.Textbox(label="Generated Completion", lines=4),
|
49 |
title="LLaMA Text Completion",
|
50 |
+
description= """\
|
51 |
+
# Llama 3.2 1B Finetuned With Evolution Learning Network (ELN)
|
52 |
+
---
|
53 |
+
This project implements an Evolution Learning Network (ELN) to fine-tune transformer-based models like LLaMA using a combination of Quantized Low-Rank Adaptation (QLoRA) and Genetic Algorithms (GA). The primary objective is to evolve a population of models across multiple generations to optimize for performance (fitness) and specialization, while maintaining diversity.
|
54 |
+
---
|
55 |
+
This is a demo of [`diabolic6045/ELN-Llama-1B-base`](https://huggingface.co/diabolic6045/ELN-Llama-1B-base).
|
56 |
+
""",
|
57 |
examples=[
|
58 |
["Once upon a time in a magical forest", 0.7, 50],
|
59 |
["The recipe for making the perfect chocolate cake requires", 0.7, 50],
|