EleutherAI pythia issues

EleutherAI / pythia

The hub for EleutherAI's work on interpretability and learning dynamics

Apache License 2.0

2.14k stars 156 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Refactoring

#168 sunnyddelight closed 5 hours ago
1
open-source the training data used between two adjacent checkpoints

#167 txy77 opened 18 hours ago
0
make README easier to follow

#166 Arvid-pku opened 3 weeks ago
1
Issue while showering NLO events with NLO

#165 rash-eng opened 3 weeks ago
0
How to use the Huggingface dataset /EleutherAI/pythia-memorized-evals in predictable-memorization?

#164 Happy2Git opened 1 month ago
0
cache_dir cannot be the same as model name

#163 arunasank opened 1 month ago
0
Pythia 12b flash config

#162 jvendrow opened 1 month ago
0
Sparse

#161 sunnyddelight closed 1 month ago
1
how to use Pythia

#160 gaohang opened 1 month ago
0
Convert to GGUF

#159 yanxon opened 2 months ago
0
Reshape error in batch viewer

#158 activatedgeek closed 2 months ago
1
Update README.md

#157 borgr closed 2 months ago
1
tokenizer.pad_token

#156 vincent317 opened 3 months ago
1
instruct-tuned pythia

#155 WilliamsToTo opened 3 months ago
0
Correct link to huggingface

#154 l-ma closed 3 months ago
1
Provide the shuffled index_mapping npy files for ease of reproducing training data

#153 ziqi-zhang opened 3 months ago
0
Optimizer states in HF format

#152 seyuboglu opened 4 months ago
1
Weird inconsistency in Tokenizer vocabulary

#151 javirandor opened 4 months ago
1
Is there existing code to resume training from specific checkpoint?

#150 javirandor closed 4 months ago
1
"gas" configuration doesn't do anything

#149 segyges opened 5 months ago
0
Adding _warmup_mmap_file function missing from MMapIndexedDataset

#148 rdiehlmartinez closed 4 months ago
1
Add training loss data

#147 pietrolesci opened 5 months ago
1
Update README.md

#146 speed1313 opened 5 months ago
1
Would it be possible to share training loss curves on the original Pythia models?

#145 itsnamgyu closed 5 months ago
4
[Pythia on Pile-Dedup] Training for ~1.5 epochs: how to identify the repeated sequences (i.e., the additional .5 epoch)?

#144 pietrolesci opened 6 months ago
3
Fix ToC

#143 osanseviero closed 6 months ago
1
Details about "EleutherAI/pythia-160m-seed*" models

#142 IanMagnusson closed 7 months ago
3
Missing / undownloadable checkpoints on huggingface

#141 mirandrom closed 5 months ago
3
.

#140 ParthaKrPaul closed 7 months ago
2
Wrong files in eval?

#139 borgr opened 7 months ago
0
Pytia or GPT-neox?

#138 borgr closed 7 months ago
1
Deduplicated Pile dataset with Domain Attribution

#137 michaelduan8 closed 7 months ago
0
Replicating the Training Data Order

#136 prakharg24 closed 7 months ago
1
Inconsistent init methods of pythia-6.9b model

#135 mqyqlx opened 7 months ago
2
Update README.md

#134 segyges closed 7 months ago
0
Add checksum for data from huggingface

#133 segyges closed 8 months ago
1
The value of weight decay

#132 yehuitang closed 8 months ago
1
Update requirements.txt

#131 segyges closed 8 months ago
0
Typos in readme.md

#130 segyges closed 8 months ago
1
Model Initialization Question

#129 yanlai00 closed 8 months ago
1
Update readme to load preshuffled datasets

#128 uSaiPrashanth closed 8 months ago
0
Has the data been shuffled?

#127 Lisennlp opened 8 months ago
2
Reading data is slowly！

#126 Lisennlp opened 8 months ago
1
Automatically calculate shard size

#125 uSaiPrashanth closed 8 months ago
0
Automatically determine shard size

#124 uSaiPrashanth closed 8 months ago
1
Batch Viewer : Why Sequence Length 2049?

#123 prakharg24 closed 8 months ago
12
The performance about pythia and LLaMA model architecture

#122 peiyingxin closed 8 months ago
1
Any results on the validation set?

#121 chujiezheng opened 9 months ago
1
README Update

#120 StellaAthena closed 8 months ago
1
Update README.md

#119 StellaAthena closed 9 months ago
0