fromziro/test-new-arch
2.58k • Updated
AI & ML interests
Building stuff.
Recent Activity
Harley-ml
updated a
model about 2 hours ago
Harley-ml
published a
model about 2 hours ago
Join request
1
#2 opened about 19 hours ago
by 
Enderchef
Harley-ml
updated a
dataset about 18 hours ago
Join request
1
#2 opened about 19 hours ago
by Enderchef
Post
843
I've left Glint Research.
After a long time in Glint Research, an entire distributed training grid built free for them, and more, I've decided that I no longer want to be affiliated with Glint Research.
More updates will follow. Comments/questions are welcome.
While you're reading this, follow these orgs! Following takes just a few seconds, and can change someone's day.
AxiomicLabs
fromziro
SupraLabs
After a long time in Glint Research, an entire distributed training grid built free for them, and more, I've decided that I no longer want to be affiliated with Glint Research.
More updates will follow. Comments/questions are welcome.
While you're reading this, follow these orgs! Following takes just a few seconds, and can change someone's day.
- 2 replies
Add tinyLM-8M-exp benchmark scores
#5 opened 18 days ago
by 
User01110
Corpus Idea
4
#1 opened 1 day ago
by Enderchef
Harley-ml
updated 3
models 1 day ago
Harley-ml
updated a
Space 2 days ago
Harley-ml
published a
dataset 3 days ago
Post
4327
Introducing GCI-Bench, Glint Research's first benchmark!
This 5000-question bench benchmarks attention and gradients; it gives a prompt and unrelated filler parts. The goal is to benchmark if the model understands and attends to the important parts more than the unimportant parts.
I've already benchmarked on the top 5 models on our Leaderboard(Glint2, Supra 50M, Glint1.3, GPT S 5M, GPT X2 125M)
Pending benchmark status at OpenEvals/README#2
Glint-Research/GCI_Bench
This 5000-question bench benchmarks attention and gradients; it gives a prompt and unrelated filler parts. The goal is to benchmark if the model understands and attends to the important parts more than the unimportant parts.
I've already benchmarked on the top 5 models on our Leaderboard(Glint2, Supra 50M, Glint1.3, GPT S 5M, GPT X2 125M)
Pending benchmark status at OpenEvals/README#2
Glint-Research/GCI_Bench
- 7 replies
Add SupraLabs/cma-8M benchmark scores
#4 opened 19 days ago
by User01110
fixed discord invite url
#1 opened 22 days ago
by Harley-ml
LyJonathan
updated a
Space 22 days ago
LyJonathan
updated a
collection 22 days ago