mlnomad/yat-mmbert-base-embedding-v1
0.3B • Updated • 37 • 1
Csaba Toth
tocsa
AI & ML interests
Training and inference
Exotics such as space state models (Samba, Mamba, Jamba, RWKV), Diffusion text, JAT SLAY
Recent Activity
liked a model about 1 month ago
mlnomad/yat-mmbert-base-embedding-v1 upvoted a paper about 1 month ago
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence upvoted a paper about 1 month ago
RWKV-7 "Goose" with Expressive Dynamic State EvolutionOrganizations
None yet
liked a
model about 1 month ago
upvoted 2
papers about 1 month ago
liked 3
models about 1 month ago
updated a
model about 1 month ago
published 13
models about 1 month ago
tocsa/atlas-dpo
Updated • 6
tocsa/atlas-sft
8B • Updated • 3
tocsa/llama-3.2-3b-pruned-distilled-fp8
3B • Updated • 13
tocsa/nemotron-3-nano-4b-pruned-distilled-fp8
3B • Updated • 9
tocsa/nemotron-3-nano-4b-fp8
4B • Updated • 12
tocsa/nemotron-3-nano-4b-int8
4B • Updated • 9
tocsa/llama-3.2-3b-pruned
3B • Updated • 6
tocsa/nemotron-3-nano-4b-depth-pruned-28
3B • Updated • 4
tocsa/nemotron-3-nano-4b-width-pruned-manual
3B • Updated • 5
tocsa/nemotron-3-nano-4b-pruned-nas
3B • Updated • 11
tocsa/nemotron-3-nano-4b-depth-pruned-manual
3B • Updated • 5
tocsa/meridian-sft
8B • Updated • 5
tocsa/meridian-dpo
Updated • 5