A set of models that can run with bounded memory
Ngoc Bui
ngocbh
AI & ML interests
None yet
Recent Activity
submitted a paper about 9 hours ago
Kalman Delta Networks: Uncertainty-aware Associative Memory commentedon a paper 4 days ago
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning authored a paper 8 days ago
Make Each Token Count: Towards Improving Long-Context Performance with KV Cache EvictionOrganizations
None yet
models 11
ngocbh/DBTrimKV-Qwen3-VL-4B-Instruct
Image-Text-to-Text • Updated • 6
ngocbh/DBTrimKV-Qwen3-VL-8B-Thinking
Image-Text-to-Text • Updated • 5
ngocbh/DBTrimKV-Qwen3-4B-Math
Text Generation • Updated • 5
ngocbh/TrimKV-DeepSeek-R1-Distill-Llama-8B
Updated • 4
ngocbh/TrimKV-Qwen3-14B-Math
Text Generation • Updated • 4
ngocbh/TrimKV-Qwen3-8B-Math
Text Generation • Updated • 5
ngocbh/TrimKV-Qwen3-4B-Instruct-2507
Text Generation • Updated • 15
ngocbh/TrimKV-Qwen3-1.7B-Math
Text Generation • Updated • 6
ngocbh/TrimKV-Qwen3-4B-Math
Text Generation • Updated • 18
ngocbh/TrimKV-Phi-3-mini-128k-instruct
Text Generation • Updated • 9
datasets 0
None public yet