issues
search
HazyResearch
/
zoology
Understand and test language model architectures on synthetic tasks.
Apache License 2.0
163
stars
28
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Possible Issue with the Mamba Initialization
#32
AlirezAkbary
opened
2 days ago
0
Fix: correct running of the example experiment
#31
AlirezAkbary
opened
5 days ago
0
Small correction for the example launcher in the readme
#30
MaxHeuillet
opened
3 weeks ago
0
Question about MQAR eval of Based
#29
Hprairie
opened
1 month ago
3
Reproducibility of ICLR Figure 2
#28
zhan8855
opened
2 months ago
2
Questions about the data lengths for Figure 2
#27
chen-yingfa
opened
7 months ago
0
arxiv24_based_figure2 'NoneType' object has no attribute 'float'
#26
yrqUni
opened
7 months ago
1
Testing `MQAR` without training?
#25
liyucheng09
closed
7 months ago
2
MQAR mamba training
#24
Moriarty0923
closed
7 months ago
1
Fix the dataconfig changes after 194a712
#23
mc-nya
opened
8 months ago
1
File has not been merged
#22
Doraemonzzz
closed
8 months ago
1
On index bug-fix of AR experiments script and corresponding paper results
#21
atsushi3110
closed
8 months ago
1
Two `head_num` variables?
#20
deklanw
closed
8 months ago
3
Port over code from based
#19
seyuboglu
closed
9 months ago
0
About mistakes in the implementation of SMA
#18
renll
opened
9 months ago
0
Pile experiment
#17
elephantmipt
closed
8 months ago
2
State Mixer
#16
edixiong
closed
9 months ago
2
Cannot run Based model
#15
Cranial-XIX
closed
8 months ago
2
Add RWKV v5.2
#14
guangyusong
closed
10 months ago
0
Added wkv_cuda.cu and wkv_op.cpp files for RWKV
#13
guangyusong
closed
10 months ago
0
CUDA implementation of TaylorExp linear attention?
#12
deklanw
closed
10 months ago
2
fix: correct memory-saving taylor forward pass
#11
deklanw
closed
10 months ago
1
Mamba MQAR evauation
#10
xtwigs
closed
10 months ago
2
Broken link
#9
thomasj02
closed
11 months ago
1
no LICENSE file
#8
crclark
closed
10 months ago
1
Positional embedding in based model?
#7
fanghgit
closed
11 months ago
1
Potential bug in data generation code?
#6
lwang2070
closed
10 months ago
1
Config files for the experiments from blog post
#5
elephantmipt
closed
11 months ago
2
Fix logging with WandB and add simple ar
#4
seyuboglu
closed
11 months ago
0
Cleanup
#3
seyuboglu
closed
11 months ago
0
Release
#2
seyuboglu
closed
11 months ago
0
Merge in mayee's changes
#1
seyuboglu
closed
1 year ago
0