deqing

mamba2-300M-v5-mamba2

0 0

Model synced from source: deqing/mamba2-300M-v5-mamba2

Updated 2026-08-21 02:51:19 +08:00

convergent-mamba2-300M-muon-original

0 0

Model synced from source: deqing/convergent-mamba2-300M-muon-original

Updated 2026-08-21 02:44:18 +08:00

convergent-mamba2-300M-adamw-original

0 0

Model synced from source: deqing/convergent-mamba2-300M-adamw-original

Updated 2026-08-21 02:43:18 +08:00

convergent-llama-300M-muon-window-2

0 0

Model synced from source: deqing/convergent-llama-300M-muon-window-2

Updated 2026-08-17 11:37:20 +08:00

llama-300M-v5-base_7

0 0

Model synced from source: deqing/llama-300M-v5-base_7

Updated 2026-06-24 10:36:20 +08:00

llama-300M-v5-addition_adamw

0 0

Model synced from source: deqing/llama-300M-v5-addition_adamw

Updated 2026-06-24 10:31:20 +08:00

llama-600M-v4-isolate

0 0

Model synced from source: deqing/llama-600M-v4-isolate

Updated 2026-06-20 18:09:25 +08:00

llama-600M-v4-original

0 0

Model synced from source: deqing/llama-600M-v4-original

Updated 2026-06-20 18:08:26 +08:00

llama-600M-v4-swap_numbers

0 0

Model synced from source: deqing/llama-600M-v4-swap_numbers

Updated 2026-06-20 18:08:23 +08:00

llama-600M-v4-isolate-old

0 0

Model synced from source: deqing/llama-600M-v4-isolate-old

Updated 2026-06-20 18:08:23 +08:00

llama-300M-v5-unk_number

0 0

Model synced from source: deqing/llama-300M-v5-unk_number

Updated 2026-06-20 18:07:22 +08:00

llama-300M-v5-unigram

0 0

Model synced from source: deqing/llama-300M-v5-unigram

Updated 2026-06-20 18:05:24 +08:00

llama-600M-v4-bigram

0 0

Model synced from source: deqing/llama-600M-v4-bigram

Updated 2026-06-20 18:05:24 +08:00

llama-300M-v5-permute

0 0

Model synced from source: deqing/llama-300M-v5-permute

Updated 2026-06-20 18:04:27 +08:00

llama-300M-v5-isolate-old

0 0

Model synced from source: deqing/llama-300M-v5-isolate-old

Updated 2026-06-20 18:04:26 +08:00