Parsa Fashi

paschrafi's activity

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

updated a collection 1 day ago

HyLo: Long-Context Aware Upcycling for Hybrid LLMs

Collection

Hybrid MLA + Gated DeltaNet / Mamba-2 models from long-context aware upcycling: up to 32x usable context with over 90% KV-cache reduction. • 14 items • Updated 1 day ago

updated a model 1 day ago

amd/HyLo-Llama-6MLA22GDN-64K-SFT

Text Generation • 4B • Updated 1 day ago • 33

published a model 1 day ago

amd/HyLo-Llama-6MLA22GDN-64K-SFT

Text Generation • 4B • Updated 1 day ago • 33

updated a model 1 day ago

amd/HyLo-Llama-6MLA22GDN-8K-SFT

Text Generation • 4B • Updated 1 day ago • 36 • 1

published a model 1 day ago

amd/HyLo-Llama-6MLA22GDN-8K-SFT

Text Generation • 4B • Updated 1 day ago • 36 • 1

updated a model 1 day ago

amd/HyLo-Llama-14MLA14GDN-64K-SFT

Text Generation • 4B • Updated 1 day ago • 33

published a model 1 day ago

amd/HyLo-Llama-14MLA14GDN-64K-SFT

Text Generation • 4B • Updated 1 day ago • 33