tatsu-lab stanford_alpaca issues

tatsu-lab / stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

https://crfm.stanford.edu/2023/03/13/alpaca.html

Apache License 2.0

29.39k stars 4.03k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

ValueError: Trying to set a tensor of shape torch.Size([32769536]) in "weight" (which has shape torch.Size([32001, 4096])), this looks incorrect.

#319 daidaiershidi opened 1 week ago
0
newUpdate

#318 MrOkay17 closed 2 months ago
0
SFT Mistral；

#317 feiying12343 opened 3 months ago
1
RuntimeError: The size of tensor a (65539072) must match the size of tensor b (262156288) at non-singleton dimension 0

#316 YuyangJ0 opened 5 months ago
0
Tensors of the same index must be on the same device and the same dtype except `step` tensors that can be CPU and float32 notwithstanding

#315 wurevvc opened 6 months ago
0
train.py fails with TypeError: Object of type Tensor is not JSON serializable

#314 khayamgondal opened 6 months ago
0
Keyword arguments {'add_special_tokens': False} not recognized.

#313 cswangxiaowei opened 7 months ago
1
openai version

#312 cswangxiaowei closed 7 months ago
1
Test

#311 kjwjeong opened 7 months ago
1
In-code documentation and linting update

#310 louisbrulenaudet opened 7 months ago
0
Update requirements.txt

#309 Ki-Seki opened 8 months ago
1
Cuda OOM during training

#308 hychaochao opened 8 months ago
0
The arugment order of Rouge score might be wrong.

#307 zhaowei-wang-nlp opened 9 months ago
0
NotImplementedError: offload_to_cpu=True and NO_SHARD is not supported yet

#306 mechigonft opened 10 months ago
1
Problems generating my own data offline

#305 JieDengsc closed 10 months ago
0
weight_diff.py state_dict_recovered[key].add_(state_dict_raw[key]) RuntimeError: The size of tensor a (32001) must match the size of tensor b (32000) at non-singleton dimension 0

#304 gaodexiaozheng opened 10 months ago
3
ImportError when using `weight_diff.py` script

#303 SebastianRiquelmeM opened 10 months ago
2
How to get the model

#302 Guo-Chenxu opened 10 months ago
0
Can you release your evaluation code and data?

#301 mshich1 opened 11 months ago
0
AttributeError: 'ModelArguments' object has no attribute 'target_modules'

#300 juzidelang opened 1 year ago
0
Confusion about instruction task

#299 mitchelldehaven closed 1 year ago
1
Loss will suddenly turn 0 during SFT

#298 zhangyx0417 closed 12 months ago
2
Utilize regen.json in finetuning

#297 Yijia-Xiao opened 1 year ago
0
How to finetune with a own private data and then build chatbot on that?

#296 rjtshrm opened 1 year ago
2
Wonder how to inference after finetuning.

#295 5taku opened 1 year ago
0
Question about padding the input sequence

#294 BaleChen opened 1 year ago
3
Python bindings and text classification & summarisation tasks

#293 Dee-Ma opened 1 year ago
0
How to provide extra contexrt as a pdf file?

#292 gamerjazzar opened 1 year ago
0
[Windows]: RuntimeError: Distributed package doesn't have NCCL built in

#291 SkibaSAY opened 1 year ago
0
BUG: "labels" information leakage into "input_ids" fields - incorrect attention_mask

#290 Nsigma-Bill closed 1 year ago
1
incorrect model_max_length

#289 joemkwon opened 1 year ago
1
DeepSpeed compilation (cpu_adam issue)

#288 JohnTailor opened 1 year ago
0
TypeError: 'type' object is not subscriptable

#287 WYXG233 opened 1 year ago
2
where did the code define the wandb?

#286 applepieiris opened 1 year ago
0
Training bug for 13b, 30b, and 65b

#285 alexgshaw opened 1 year ago
5
Location of Log Files for the model?

#284 harshaelon opened 1 year ago
0
How to classify all the data?

#283 rayrayraykk opened 1 year ago
0
how to determine the basis of fine-tuen is enough?

#282 aijianiula0601 opened 1 year ago
0
Why do we pass both question and answer as input to the model during training?

#281 ruiyigan opened 1 year ago
0
Finetune with A100 40G

#280 jianchaoji opened 1 year ago
4
How to finetune using the customizer data?

#279 JustinZou1 opened 1 year ago
0
The OOM problem caused by the Transformers version

#278 kiseliu opened 1 year ago
2
why I save two pytorch_model.bin with same size

#277 qwjaskzxl opened 1 year ago
0
Inquiry about license

#276 CallMeDek opened 1 year ago
1
Why the model I got after finetune is not good

#275 wyzhhhh opened 1 year ago
0
Add accelerate to requirements.txt

#274 Kh4L opened 1 year ago
0
encounter errors when I try to finetune the model

#273 SleepEarlyLiveLong opened 1 year ago
2
Older Mac

#272 betolley closed 1 year ago
2
how to train alpaca with single GPU A100 without FSDP?

#271 moseshu opened 1 year ago
0
How to fine tuning th model with limited resource?

#270 GivanTsai opened 1 year ago
1