issues
search
EleutherAI
/
pythia
The hub for EleutherAI's work on interpretability and learning dynamics
Apache License 2.0
2.23k
stars
164
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Reading data is slowly!
#126
Lisennlp
opened
11 months ago
1
Automatically calculate shard size
#125
uSaiPrashanth
closed
11 months ago
0
Automatically determine shard size
#124
uSaiPrashanth
closed
11 months ago
1
Batch Viewer : Why Sequence Length 2049?
#123
prakharg24
closed
11 months ago
15
The performance about pythia and LLaMA model architecture
#122
peiyingxin
closed
11 months ago
1
Any results on the validation set?
#121
chujiezheng
opened
12 months ago
1
README Update
#120
StellaAthena
closed
11 months ago
1
Update README.md
#119
StellaAthena
closed
1 year ago
0
Mismatch about the evaluation results
#118
yuzc19
closed
11 months ago
11
Weights tying
#117
link-er
closed
1 year ago
1
Convert the huggingface checkpoint to GPT-Neox checkpoint
#116
ZhiYuanZeng
closed
1 year ago
2
Clarification of Pythia tokenizer(s) at different sizes, steps and data preprocessing?
#115
RylanSchaeffer
closed
1 year ago
1
Error when running unshard_memmap.py
#114
ShaneeyS
closed
11 months ago
2
Can I provide custom data and continue training Pythia on this new data?
#113
GeorgiAngelov
closed
1 year ago
1
Difference between LFS and HuggingFace datasets?
#112
eric-mitchell
closed
1 year ago
1
Batch viewer
#111
uSaiPrashanth
closed
1 year ago
0
Multiple training runs of same model with different random seed for weight initialisation
#110
KarolisRam
closed
1 year ago
1
Update documentation for installing `batch_viewer.py` deps
#109
haileyschoelkopf
closed
1 year ago
0
Possible error in Pythia-12B-deduped step 32000
#108
smahdavi4
closed
1 year ago
2
pythia-12b checkpoints missing on HuggingFace for step4000 and step32000
#107
byungdoh
closed
1 year ago
2
Is there a template poilerplate for the prompt used in C.1 gender bias intervention?
#106
ruyuan-zuo
closed
1 year ago
1
Draft new repo structure
#105
haileyschoelkopf
closed
1 year ago
2
Add Memorization Evals to repo
#104
uSaiPrashanth
closed
1 year ago
1
Added instructions for reproducing a Pythia training
#103
BaruchG
closed
1 year ago
1
Train/valid/test split
#102
choidami
closed
1 year ago
1
release of checkpoints of different steps
#101
TobiasLee
closed
1 year ago
5
Ensure flash attention in configs
#100
haileyschoelkopf
closed
1 year ago
0
Revamp experiment organization and migrate code when necessary
#99
StellaAthena
closed
1 year ago
0
Will memorization experimental codes be released?
#98
chujiezheng
closed
1 year ago
2
the loss of pythia training
#97
Wangpeiyi9979
closed
1 year ago
3
Fine-tuning recommendations
#96
RainIwakura
closed
1 year ago
2
Update License
#95
StellaAthena
closed
1 year ago
1
Pythia 6.9B Model Missing Checkpoint
#94
chujiezheng
closed
1 year ago
1
Update README.md to remove work-in-progress disclaimer
#93
haileyschoelkopf
closed
1 year ago
1
Is there an access to the deduplicated version of the data with meta info?
#92
Jason3900
closed
1 year ago
6
Add a citation to Readme
#91
haileyschoelkopf
closed
1 year ago
0
Cleanup old files
#90
haileyschoelkopf
closed
1 year ago
0
Fine tune for text generation on custom data
#89
samarthsarin
closed
1 year ago
1
Add paper to README
#88
Quentin-Anthony
closed
1 year ago
0
Training time or approximation of TFLOPs?
#87
zetian1025
closed
1 year ago
2
training logs
#86
stjaco
closed
1 year ago
1
Are pythia_v0 and the new pythia_v1 models using the same input embedding matrix?
#85
levmckinney
closed
1 year ago
3
Update README.md
#84
eltociear
closed
1 year ago
0
Weights of "step0" and "step1" checkpoints are identical for all pythia models
#83
byungdoh
closed
1 year ago
6
Add changelog section to README
#82
haileyschoelkopf
closed
1 year ago
0
Mistake in readme
#81
zplizzi
closed
1 year ago
1
reorganize v1.1 eval files
#80
haileyschoelkopf
closed
1 year ago
0
Add more details for reproducing training runs
#79
zplizzi
closed
1 year ago
5
Crowspairs Old with More Steps
#78
aflah02
closed
10 months ago
2
Crowspair Plots
#77
aflah02
closed
11 months ago
2
Previous
Next