karpathy nanoGPT issues

karpathy / nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

MIT License

37.49k stars 5.97k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Merge for comprehension when filtering parameters without grad

#574 tsdeng opened 1 day ago
0
Oren/amd mess

#573 OrenLeung closed 1 week ago
0
Oren/config

#572 OrenLeung closed 1 week ago
0
cancel

#571 Zhao-Yuting closed 1 week ago
0
NaniGpt

#570 ashokkumar272 opened 3 weeks ago
0
added fix to type comparison to enable fused AdamW

#569 seanjudelyons opened 3 weeks ago
0
Spring cleaning

#568 ckgresla closed 3 weeks ago
0
How best to implement a differential transformer?

#567 Wilsontomass opened 1 month ago
2
the things

#566 drisspg closed 1 month ago
0
Normalized gpt

#565 santiagoakle closed 4 weeks ago
1
Ddp do not sync when not needed

#564 OrenLeung closed 1 month ago
0
Refactor to stop inductor mess

#563 OrenLeung closed 1 month ago
0
Moe

#562 hellozmz closed 1 month ago
0
Clean

#561 simran-arora closed 1 month ago
0
Windows 11: FileExistsError: [WinError 183] Cannot create a file when that file already exists

#560 VyBui opened 1 month ago
1
Update README.md

#559 eshwarram closed 1 month ago
0
Updated README.md to include table of contents, why this project is useful, and how to contribute, and added an output for one command

#558 arhaque09 opened 1 month ago
0
Updated README.md to include table of contents, why this project is useful, and how to contribute

#557 arhaque09 closed 1 month ago
0
Updated README.md to include table of contents, why this project is useful, and how to contribute

#556 arhaque09 closed 1 month ago
0
Adding NVIDIA hardware performance detection

#555 fparisio opened 2 months ago
0
Pretraining loss explosion

#554 mattgorb opened 2 months ago
1
Add fire finetuning

#553 gkielian opened 2 months ago
0
why is the warmup_iters set 2000?

#552 luxunxiansheng opened 2 months ago
0
The Positional Encoding is not using sin / cos?

#551 mw66 opened 2 months ago
1
Remove flashattention from model.py

#550 chughtapan closed 2 months ago
0
Implement muP and add code for mup guide blog

#549 ndey96 closed 2 months ago
0
Perplexity

#548 Precola opened 2 months ago
0
Progressive training?

#547 immartian opened 3 months ago
4
Add support for 0 temperature

#546 jmccrosky opened 3 months ago
0
torchrun on L40S Error:torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

#545 Precola closed 3 months ago
1
Rocm support?

#544 ilovethensa opened 3 months ago
0
Calculation of Batch Size

#543 Precola closed 3 months ago
1
configuration for Macs(apple silicon)

#542 bawsi99 opened 3 months ago
0
Adding gpt2 training experiment

#541 NewtonSander closed 3 months ago
0
Use weights_only for loading

#540 kit1980 opened 3 months ago
0
What to change for training on two T4 GPUs ?

#539 noorchauhan opened 3 months ago
1
Update train.py for more efficiency

#538 Jesseonmi opened 4 months ago
0
Simple Use Case Demonstration with Old School Runescape Terminology

#537 Omarch47 opened 4 months ago
0
Solution to Exercise 1 from Youtube Lecture (Batching the heads) - Why does it work?

#536 Andrew-Luo1 closed 4 months ago
1
Nano GPT

#535 phanee123 opened 4 months ago
0
ddp on macbook CPU

#534 langong347 closed 4 months ago
0
free up state_dict variable memory after loading checkpoint

#533 adistomar opened 4 months ago
0
FileNotFoundError: [Errno 2] No such file or directory: 'data/openwebtext/train.bin'

#532 HarikrishnanK9 opened 4 months ago
1
About the get_batch

#531 leo-young opened 4 months ago
1
Add automatic detection of number of CPU cores

#530 Jakobovski opened 4 months ago
1
Data cleaning for openwebtext

#529 zzkzzkjsw opened 4 months ago
0
fix val dataset size code comment

#528 vhmth opened 5 months ago
0
fix(train.py): mfu estimation to respect CPU-GPU sync point

#527 JasonLiJT opened 5 months ago
0
code gpt v1

#526 shatrugna closed 5 months ago
0
"RuntimeError: Internal Triton PTX codegen error" is raised when I train shakespeare_char with a GPU

#525 shenbb opened 5 months ago
5