2
Repos
26
Stars
1
Forks
0
Watchers
🏆 Show off this rank
Add it to a GitHub README or profile — the card updates as the ranking changes:
Repositories (2)
sparse-memory-lm
re133/sparse-memory-lm
Python
A 21M-parameter LM with a 16.8M-row product-key memory: as good as a 114M dense model and runs with the table on an SSD. Triton kernels for ROCm and CUDA.
16
1
red-curtain
re133/red-curtain
Python
Run Fish Audio Drama 3 locally on AMD GPUs (ROCm). 16 GB VRAM is enough, the MoE experts live in RAM. Community project, not affiliated with Fish Audio.
10
0