EleutherAI gpt-neo issues

EleutherAI / gpt-neo

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

https://www.eleuther.ai

MIT License

8.21k stars 945 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Cannot Connect To Local TPU-VM

#323 nikhilanayak opened 2 years ago
1
FYI:Japanese pre-trained gpt-neo implementation showcase by using PyTorch, Transformers, and Rust

#322 ycat3 closed 2 years ago
1
Bump tensorflow from 2.5.1 to 2.5.3

#321 dependabot[bot] opened 2 years ago
0
IndexError: index out of range in self

#273 dzlab opened 2 years ago
1
TPU device does not support heartbeats.

#272 iliemihai opened 2 years ago
0
The model should return just the generated text, not the prompt text + generated text.

#271 monsieurpooh opened 2 years ago
2
The temperature at 0.0001 (or other arbitrarily small float) is still too high

#270 monsieurpooh opened 2 years ago
5
Not able to generate predicted text after `Done with copy master to slices.` with 1.3B pre-trained model

#269 SanchiMittal opened 2 years ago
0
Generation should allow user to specify max length of generated portion, rather than total

#268 monsieurpooh closed 2 years ago
5
The locally ran gpt-neo-2.7B is using CPU instead of GPU

#267 monsieurpooh closed 2 years ago
1
Argument not a list with same length as devices

#266 monsieurpooh opened 2 years ago
0
Links in the readme to the-eye.eu don't work

#265 monsieurpooh opened 2 years ago
1
GPT-neo 350M weights?

#264 gangiswag closed 2 years ago
3
the-eye.eu is down again, is there a mirror?

#263 nepeee closed 2 years ago
6
GPT3_1_3B configuration for a v3-32 TPU

#262 iliemihai closed 2 years ago
3
Colab: Download of pre trained dataset not possible. the-eye.eu is offline

#261 JonasPertschy closed 2 years ago
1
Incosistent inference TPU vs GPU (huggingface)

#260 vvv-tech closed 2 years ago
1
Freeze Transformer Weight

#259 ivokun closed 2 years ago
1
Inferencing

#258 BakingBrains closed 2 years ago
2
Dataset preparation

#257 BakingBrains closed 2 years ago
1
Exception: stream did not contain valid UTF-8

#256 BakingBrains closed 2 years ago
0
Bump tensorflow from 2.5.1 to 2.5.2

#255 dependabot[bot] closed 2 years ago
1
removed a consider-using-in pitfall case

#252 NaelsonDouglas closed 2 years ago
0
Predict runtime error

#251 Borshig closed 2 years ago
2
How to fine tine gptneo for QA dataset?

#250 shankyemcee closed 2 years ago
3
Issues with Argument defaulting in `data/create_tfrecords.py`

#249 reshinthadithyan closed 2 years ago
1
How to do few shot in context learning using GPT-NEO

#248 yananchen1989 closed 2 years ago
2
Error when connecting to Google Cloud Storage

#247 goaaats closed 3 years ago
1
improved metrics table

#246 redthing1 closed 3 years ago
0
Where to download model for EleutherAI/gpt-j-6B

#245 AlexanderKozhevin closed 3 years ago
1
Update tasks.py

#244 DLPerf closed 2 years ago
0
Bug in Google Colab

#243 vnitu02 closed 3 years ago
0
Bump tensorflow from 2.5.0 to 2.5.1

#242 dependabot[bot] closed 3 years ago
0
[colab notebooks] Can't restore pretrained weights

#241 sky1ove closed 2 years ago
2
Performance issue in tasks.py

#240 DLPerf closed 2 years ago
4
Performance issues in the program

#239 DLPerf closed 2 years ago
2
Where to download 125M model? thanks.

#238 tamal777 closed 3 years ago
2
fixes "IndexError: list index out of range"

#237 mgrankin closed 3 years ago
0
Issue loading gpt-neo-125M from checkpoint

#236 ixn872 closed 3 years ago
0
Have any GPTNeoForCausalLM training example in pytorch with hardware acceleration?

#235 Pwang001 closed 2 years ago
1
Is It Possible To Continue Finetuning From Checkpoints on Any GPT-Neo Model?

#234 nikhilanayak closed 3 years ago
1
Tokenizing error when training on Colab

#233 Marcus-Arcadius closed 2 years ago
8
Finetuning doesn't run

#232 SamyakDhole closed 2 years ago
4
The_Eye hosted models wont download

#231 diskreet90 closed 2 years ago
3
Fix trailing token bug in create_tfrecords

#230 nostalgebraist closed 3 years ago
1
How can I get train data?

#229 thefreeman007 closed 3 years ago
1
Enable GPT-Neo-125M for downstream training Effectively

#228 bhadreshpsavani closed 2 years ago
0
Using gpt neo checkpoint

#227 MK096 closed 3 years ago
9
Can't load GPT3_XL

#226 MK096 closed 3 years ago
7
[Data] create tfrecords: fail fast when no files are found

#225 louis030195 closed 3 years ago
0