stanfordnlp pyreft issues

stanfordnlp / pyreft

ReFT: Representation Finetuning for Language Models

https://arxiv.org/abs/2404.03592

Apache License 2.0

942 stars 76 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[P1] Contact information

#116 automateyournetwork closed 1 week ago
1
[P1] Error(s) in loading state_dict for Linear

#115 Hamana0509 opened 1 week ago
2
[P1] Unable to replicate results from paper for RoBERTa Base for Glue tasks like CoLa

#114 m-dev12 closed 1 week ago
8
[P1] Getting key error in parameter while training REFT using LLAMA3

#113 AkashGhosh opened 1 week ago
4
[P1] Loading ReFT for Llama3 model after fine-tuned with ReFT and LoRA

#112 Hamana0509 closed 1 week ago
3
[P1] If set output_original_output to True in intervenable.generate, can we get the model performance without intervention?

#111 mrsempress closed 1 week ago
1
[P1] For left_padding in compute_metrics.py

#110 mrsempress opened 2 weeks ago
2
[P1] Refactor ReftTrainer to save artifacts with the config

#109 BryanWBear opened 2 weeks ago
1
Fix: datasets.exceptions.DatasetNotFoundError when training with alpaca_data_cleaned

#108 savadikarc closed 2 weeks ago
0
[P1] Experimental setup for instruction following experiments in the ReFT paper

#107 savadikarc closed 2 weeks ago
3
[P1] TypeError: Object of type type is not JSON serializable

#106 ajayspatil7 closed 3 weeks ago
4
[P1] Possible to do batch inference?

#105 thistleknot opened 3 weeks ago
3
[Major][pyreft-core] ReFT next release items

#104 frankaging opened 3 weeks ago
1
[P0] Revert back to ortho init as unstable training

#103 frankaging closed 3 weeks ago
0
[P1] [Error] can not use bfloat16 and TypeError: Object of type type is not JSON serializable

#102 mrsempress closed 2 weeks ago
21
transformers_modules.microsoft.Phi-3-mini-4k-instruct.d269012bea6fbe38ce7752c8940fea010eea3383.modeling_phi3.Phi3ForCausalLM

#101 thistleknot closed 4 weeks ago
1
[Minor] Basic support of quantization

#100 frankaging closed 4 weeks ago
0
[P1] Is it possible to merge the base model + REFT model into only model?

#99 celsowm closed 4 weeks ago
1
[P1] Loss decrease slow in readme demo when use NousResearch/Llama-2-7b-chat-hf

#98 svjack closed 4 weeks ago
2
[P0] Does this project support turning in 4bit or 8bit Quantify？

#97 svjack closed 4 weeks ago
5
[P1] Multiple Positions Intervention

#96 comeandcode closed 4 weeks ago
1
[P1] Questions on differences between paper and code

#95 calpt closed 1 month ago
2
[Minor] Enable lora with loreft training

#94 frankaging closed 1 month ago
0
[P1] support ReFT+PEFT by using ReftModel to wrap PeftModel (#46)

#93 frankaging closed 1 month ago
1
[P1] Transitioning from peft to pyreft for Classification Approach

#92 SaBay89 opened 1 month ago
2
[P1] Model Compatibility

#91 SaBay89 closed 1 month ago
2
forward() got an unexpected keyword argument 'unit_locations'

#90 xerkey closed 1 month ago
2
Title: Fix: Shape Mismatch during Left Padding Adjustment in compute_metrics (Generated by Ana - AI SDE)

#89 ana-ai-sde closed 1 month ago
3
[P1] Loreft example gsm8k train gives: RuntimeError: output with shape [64, 1, 7] doesn't match the broadcast shape [64, 0, 7]

#88 jaymefosa closed 1 month ago
3
[P1] TypeError: train() takes 1 positional argument but 2 were given

#87 alpozdarendeli closed 1 month ago
1
[P1] Loading REFT fro RoBERTa Models

#86 hSterz opened 1 month ago
3
[P0] Make `make_last_position_supervised_data_module` parallelizable to speed up processing!

#85 truskovskiyk opened 1 month ago
2
[P1] Convert reft model to hf model

#84 thu-yn closed 4 weeks ago
1
[P1] Getting error as IntervenableModel.train() takes 1 positional argument but 2 were given

#83 atharvapatiil closed 1 month ago
4
[P0] Additional intervention arguments are not saved correctly, e.g. `add_bias`

#82 frankaging opened 1 month ago
0
[P1] How did you create the validation set for Commonsense reasoning hyperparameter tuning?

#81 Edenzzzz closed 1 month ago
5
Getting issue while loading Phi3 in reft_model

#80 atharvapatiil closed 1 month ago
9
[P1] RuntimeError: cutlassF: no kernel found to launch!

#79 ds-praveenkumar closed 1 month ago
4
[P1] catastrophic forgetting

#78 jiacheo closed 1 month ago
1
[P1] Intuitive-wise, should we keep the projection orthogonal during training?

#77 Edenzzzz closed 1 month ago
2
ReFT + DPO Tutorial

#76 AmirZur closed 1 month ago
1
[Minor] fix subspace (#72)

#75 frankaging closed 2 months ago
1
[Minor] More refactory to support Llama3 experiments

#74 frankaging closed 2 months ago
0
[P1] Confirmation of alpaca_eval version

#73 BaohaoLiao closed 2 months ago
4
[P0] compreft.ipynb error = KeyError: 'subspaces'

#72 RonanKMcGovern closed 1 month ago
4
[P1] Location of code for "LM training and serving with ReFT"

#71 RonanKMcGovern opened 2 months ago
2
[P2] Pyreft tensorboard integration

#70 PinetreePantry opened 2 months ago
0
[P1] TypeError: Object of type type is not JSON serializable

#69 srn-source closed 2 months ago
7
[P0] Why is the number of trainable parameters for prefix-tuning is 0.11%

#67 BaohaoLiao closed 2 months ago
7
[P0] Adding DPO Support

#66 jinzhuoran closed 1 month ago
8