Key-Value Means
Paper • 2605.09877 • Published • 21 •
2
Ernigma Bhallz
Ernigma
·
AI & ML interests
LLM models for personal assistants
Recent Activity
commentedon a paper about 5 hours ago
Key-Value Means upvoted a paper about 5 hours ago
Key-Value Means new activity about 1 month ago
trohrbaugh/gemma-4-26B-A4B-it-heretic-ara-v2:Whats new with the v2?Organizations
None yet
commented a
paper about 5 hours ago
upvoted a paper about 5 hours ago
Whats new with the v2?
1
#1 opened about 1 month ago
by Ernigma
liked a
dataset 4 months ago
🚩 Report: Illegal or restricted content
🤝 1
5
#1 opened 4 months ago
by 
yukiarimo
No base model
👍 15
8
#2 opened 8 months ago
by 
ricardo-rei
liked 2
datasets 8 months ago
reacted to elinas's post with 🚀👀 over 1 year ago
Post
3106
We conducted an experiment in an effort to revive LLaMA 1 33B as it had unique prose and a lack of "GPT-isms" and "slop" in its pretraining data, as well as being one of the favorites at the time. With multiple finetune runs, we were able to extend the model from it's pretrained base of 2048 to ~12,000 tokens adding approx. 500M tokens in the process. The effective length is 16,384 but it's better to keep it on the lower range. It writes well and in multiple formats. In the future, we have some ideas like implementing GQA. Please take a look and we would love to hear your feedback!
ZeusLabs/Chronos-Divergence-33B
ZeusLabs/Chronos-Divergence-33B