hexgrad/Kokoro-82M
Text-to-Speech
•
Updated
•
9.72k
•
747
spooner
spooner2
AI & ML interests
None yet
Recent Activity
liked
a model
7 days ago
hexgrad/Kokoro-82M
Organizations
None yet
spooner2's activity
liked
a
model
7 days ago
upvoted
a
paper
2 months ago
reacted to
yongchanghao's
post with 🔥
2 months ago
Post
3754
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)
Read more about the work at NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks (2410.20650)
liked
a
model
5 months ago
combined safetensors , but comfyui issue a error.
9
#3 opened 5 months ago
by
demo001s
liked
2
models
5 months ago
liked
a
model
7 months ago
liked
a
model
8 months ago
reacted to
codelion's
post with 🚀
9 months ago
Post
1759
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!
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