Pythia 160M, Mamba 130M, and RWKV 169M models trained on OpenWebText for 4000 steps (context window: 1024; effective batch size: 512). 6 seeds each.
James Michaelov
jmichaelov
AI & ML interests
None yet
Recent Activity
updated
a model
about 12 hours ago
jmichaelov/pythia31m_b128_constant_seed0
published
a model
about 12 hours ago
jmichaelov/pythia31m_b128_constant_seed0
updated
a model
about 12 hours ago
jmichaelov/pythia31m_b16_constant_seed0
Organizations
models
53
jmichaelov/pythia31m_b128_constant_seed0
30.5M
•
Updated
•
16
jmichaelov/pythia31m_b16_constant_seed0
30.5M
•
Updated
•
17
jmichaelov/pythia31m_b32_constant_seed2
30.5M
•
Updated
•
16
jmichaelov/pythia31m_b1024_64_constant_seed1
30.5M
•
Updated
•
15
jmichaelov/pythia31m_b512_constant_seed1
30.5M
•
Updated
•
17
jmichaelov/pythia31m_b256_constant_seed2
30.5M
•
Updated
•
15
jmichaelov/pythia31m_b64_constant_seed1
30.5M
•
Updated
•
17
jmichaelov/pythia31m_b16_constant_seed3
30.5M
•
Updated
•
15
jmichaelov/pythia31m_b128_constant_seed3
30.5M
•
Updated
•
16
jmichaelov/pythia31m_b1024_64_constant_seed2
30.5M
•
Updated
•
16
datasets
13
jmichaelov/bhs
Viewer
•
Updated
•
22k
•
48
•
1
jmichaelov/blimp_nl
Viewer
•
Updated
•
8.4k
•
86
jmichaelov/lm_syneval
Viewer
•
Updated
•
158k
•
28
jmichaelov/inverse_scaling_prize-hindsight_neglect
Viewer
•
Updated
•
315
•
4
jmichaelov/inverse_scaling_prize-memo_trap
Viewer
•
Updated
•
936
•
5
jmichaelov/inverse_scaling_prize-neqa
Viewer
•
Updated
•
300
•
9
jmichaelov/inverse_scaling_prize-redefine
Viewer
•
Updated
•
1.24k
•
7
jmichaelov/inverse_scaling_prize-into_the_unknown
Viewer
•
Updated
•
1.82k
•
4
jmichaelov/inverse_scaling_prize-modus_tollens
Viewer
•
Updated
•
1.24k
•
4
jmichaelov/inverse_scaling_prize-pattern_matching_suppression
Viewer
•
Updated
•
1.43k
•
6