spooner

spooner2's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a paper 26 days ago

OmniGen: Unified Image Generation

Paper • 2409.11340 • Published Sep 17 • 108

Reacted to yongchanghao's post with 🔥 27 days ago

view post

Post

3734

Reply

We just released a paper (NeuZip) that compresses VRAM in a lossless manner to run larger models. This should be particularly useful when VRAM is insufficient during training/inference. Specifically, we look inside each floating number and find that the exponents are highly compressible (as shown in the figure below).

Read more about the work at NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks (2410.20650)

• 

🔥

18

18

👀

3

3

+

liked a model 3 months ago

alvdansen/flux-koda

Text-to-Image • Updated Aug 16 • 36.6k • • 205

New activity in HaileyStorm/FLUX.1-Merges 4 months ago

combined safetensors , but comfyui issue a error.

9

#3 opened 4 months ago by demo001s

liked 2 models 4 months ago

black-forest-labs/FLUX.1-dev

Text-to-Image • Updated Aug 16 • 1.33M • • 6.78k

black-forest-labs/FLUX.1-schnell

Text-to-Image • Updated Aug 16 • 2.08M • • 2.94k

liked a model 6 months ago

stabilityai/stable-diffusion-3-medium

Text-to-Image • Updated Aug 12 • 34.2k • 4.59k

liked a model 7 months ago

ResplendentAI/SOVL_Llama3_8B

Text Generation • Updated Apr 25 • 18 • 33

Reacted to codelion's post with 🚀 7 months ago

view post

Post

1759

Reply

Happy to announce the open source framework to turbo charge devops called patchwork - https://github.com/patched-codes/patchwork

You can use it to build patchflows - workflows that use LLMs for software development tasks like bug fixing, pull request review, library migration and documentation.

Supports any LLM of your choice including our own MoE model - patched-codes/patched-mix-4x7B

Give it a try!

• 
• 
• 2 replies

·

🔥

4

4

🚀

3

3

+