Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -4,6 +4,11 @@ import torch
|
|
| 4 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 5 |
|
| 6 |
title = """# ππ»ββοΈ Welcome to Tonic's Minitron-8B-Base"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
# Load the tokenizer and model
|
| 9 |
model_path = "nvidia/Minitron-8B-Base"
|
|
|
|
| 4 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 5 |
|
| 6 |
title = """# ππ»ββοΈ Welcome to Tonic's Minitron-8B-Base"""
|
| 7 |
+
description = """
|
| 8 |
+
Minitron is a family of small language models (SLMs) obtained by pruning [NVIDIA's](https://huggingface.co/nvidia) Nemotron-4 15B model. We prune model embedding size, attention heads, and MLP intermediate dimension, following which, we perform continued training with distillation to arrive at the final models.
|
| 9 |
+
### Join us :
|
| 10 |
+
πTeamTonicπ is always making cool demos! Join our active builder's π οΈcommunity π» [](https://discord.gg/GWpVpekp) On π€Huggingface:[MultiTransformer](https://huggingface.co/MultiTransformer) On πGithub: [Tonic-AI](https://github.com/tonic-ai) & contribute toπ [BuildTonic](https://github.com/buildtonic/)π€Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant π€
|
| 11 |
+
"""
|
| 12 |
|
| 13 |
# Load the tokenizer and model
|
| 14 |
model_path = "nvidia/Minitron-8B-Base"
|