Great article, thanks for sharing.
I am wondering why the finetuning was done on Instruct models rather than the base models?
Ahmad Khan
ahkhan
·
AI & ML interests
None yet
Recent Activity
new activity
9 days ago
nanotron/ultrascale-playbook:Fix typo in memory footprint variable name
commented on
an
article
18 days ago
Fine-tuning LLMs to 1.58bit: extreme quantization made easy
upvoted
an
article
18 days ago
Fine-tuning LLMs to 1.58bit: extreme quantization made easy
Organizations
None yet
Fix typo in memory footprint variable name
1
#115 opened 9 days ago
by
ahkhan
commented on
Fine-tuning LLMs to 1.58bit: extreme quantization made easy
18 days ago
upvoted
an
article
18 days ago
Article
Fine-tuning LLMs to 1.58bit: extreme quantization made easy
By
and 5 others
•
•
261
upvoted
a
collection
18 days ago
liked
a
Space
about 1 month ago