Issues

• Do you have test case datasets?

  tatsu-lab/stanford_alpaca#331 · Filter by author StuRinDQB opened on Sep 21, 2026

• I have a question regarding the VRAM requirements for fine-tuning a 7B model.

  tatsu-lab/stanford_alpaca#322 · Filter by author mangyeong opened on Jan 15, 2025
  1

• why dose my finetuned model repeat the given prompt before generating its response

  tatsu-lab/stanford_alpaca#320 · Filter by author starrlee356 opened on Dec 5, 2024
  1

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

  tatsu-lab/stanford_alpaca#319 · Filter by author daidaiershidi opened on Sep 26, 2024
  3

• SFT Mistral；

  tatsu-lab/stanford_alpaca#317 · Filter by author feiying12343 opened on Jun 6, 2024
  2

• RuntimeError: The size of tensor a (65539072) must match the size of tensor b (262156288) at non-singleton dimension 0

  tatsu-lab/stanford_alpaca#316 · Filter by author YuyangJ0 opened on Apr 16, 2024

• 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

  tatsu-lab/stanford_alpaca#315 · Filter by author wurevvc opened on Mar 18, 2024
  2

• train.py fails with TypeError: Object of type Tensor is not JSON serializable

  tatsu-lab/stanford_alpaca#314 · Filter by author khayamgondal opened on Mar 8, 2024
  1

• Keyword arguments {'add_special_tokens': False} not recognized.

  tatsu-lab/stanford_alpaca#313 · Filter by author cswangxiaowei opened on Mar 2, 2024
  2

• Cuda OOM during training

  tatsu-lab/stanford_alpaca#308 · Filter by author hychaochao opened on Jan 31, 2024

• The arugment order of Rouge score might be wrong.

  tatsu-lab/stanford_alpaca#307 · Filter by author zhaowei-wang-nlp opened on Dec 28, 2023

• NotImplementedError: offload_to_cpu=True and NO_SHARD is not supported yet

  tatsu-lab/stanford_alpaca#306 · Filter by author mechigonft opened on Nov 28, 2023
  1

• 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

  tatsu-lab/stanford_alpaca#304 · Filter by author gaodexiaozheng opened on Nov 22, 2023
  3

• ImportError when using weight_diff.py script

  tatsu-lab/stanford_alpaca#303 · Filter by author SebastianRiquelmeM opened on Nov 20, 2023
  2

• How to get the model

  tatsu-lab/stanford_alpaca#302 · Filter by author Guo-Chenxu opened on Nov 15, 2023

• Can you release your evaluation code and data?

  tatsu-lab/stanford_alpaca#301 · Filter by author mshich1 opened on Oct 23, 2023

• AttributeError: 'ModelArguments' object has no attribute 'target_modules'

  tatsu-lab/stanford_alpaca#300 · Filter by author juzidelang opened on Sep 22, 2023

• Utilize regen.json in finetuning

  tatsu-lab/stanford_alpaca#297 · Filter by author Yijia-Xiao opened on Aug 2, 2023

• How to finetune with a own private data and then build chatbot on that?

  tatsu-lab/stanford_alpaca#296 · Filter by author rjtshrm opened on Jul 30, 2023
  2

• Wonder how to inference after finetuning.

  tatsu-lab/stanford_alpaca#295 · Filter by author 5taku opened on Jul 26, 2023

• Question about padding the input sequence

  tatsu-lab/stanford_alpaca#294 · Filter by author BaleChen opened on Jul 20, 2023
  3

• Python bindings and text classification & summarisation tasks

  tatsu-lab/stanford_alpaca#293 · Filter by author Dee-Ma opened on Jul 18, 2023

• How to provide extra contexrt as a pdf file?

  tatsu-lab/stanford_alpaca#292 · Filter by author gamerjazzar opened on Jul 11, 2023

• [Windows]: RuntimeError: Distributed package doesn't have NCCL built in

  tatsu-lab/stanford_alpaca#291 · Filter by author SkibaSAY opened on Jul 11, 2023

• incorrect model_max_length

  tatsu-lab/stanford_alpaca#289 · Filter by author joemkwon opened on Jun 28, 2023
  1