6 repos
whynlp/tinyllama-lckv-w10-100b
No description
0
5 commits
whynlp/tinyllama-lckv-w2-ft-100b
14 commits
whynlp/tinyllama-lckv-w2-100b
6 commits
whynlp/tinyllama-lckv-w10-ft-250b
whyNLP/LCKV
Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic…
156
185 commits
Snowflake/Llama-3.1-SwiftKV-8B-Instruct
8
28 commits