josephmayo/gemma-4-E4B-it-Coder
Image-Text-to-Text • 8B • Updated • 186 • 1
josephmayo
josephmayo
AI & ML interests
why dont we make sota models that can fit on consumer hardware
Recent Activity
updated a model 3 days ago
josephmayo/gemma-4-E4B-it-Coder liked a model 3 days ago
microsoft/Fara-7B new activity 4 days ago
mradermacher/model_requests:quants for https://huggingface.co/josephmayo/gemma-4-E4B-it-CoderOrganizations
None yet
updated a
model 3 days ago
liked a
model 3 days ago
quants for https://huggingface.co/josephmayo/gemma-4-E4B-it-Coder
1
#2382 opened 4 days ago
by josephmayo
updated 2
models 4 days ago
published a
model 5 days ago
liked a
model 6 days ago
published 2
models 6 days ago
reacted to danielhanchen's post with 🔥 8 days ago
Post
7572
We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! 🚀
Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing
Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth
Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing
Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth
quantized and RSA
2
#5 opened 10 days ago
by 
ainz
liked a
model 11 days ago
upvoted a collection 13 days ago
the 2/3 bits are unusable
#1 opened 15 days ago
by josephmayo
why??
👀 1
1
#12 opened 15 days ago
by josephmayo
the "aggressive"
#20 opened 15 days ago
by josephmayo
Balanced version
4
#19 opened 17 days ago
by 
svarognsa
updated a
model 16 days ago
published a
model 16 days ago
updated a
model 16 days ago