Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
samwit
/
bloompaca-7b1-lora
like
0
Model card
Files
Files and versions
Community
samwit
commited on
Mar 18, 2023
Commit
e10a2fe
•
1 Parent(s):
9fbb77a
Create README.md
Browse files
Files changed (1)
hide
show
README.md
+4
-0
README.md
ADDED
Viewed
@@ -0,0 +1,4 @@
1
+
2
+
This is a LoRa finetuning of Bloom-7b1 using the Alpaca instruction dataset.
3
+
4
+
It really highlights how the Bloom models are undertrained with ~400M tokens as opposed to 1 Trillion in the smaller LLaMa models.