Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / stanfordnlp/pyreft issues and pull requests
#111 - If set output_original_output to True in intervenable.generate, can we get the model performance without intervention?
Issue -
State: open - Opened by mrsempress 14 days ago
#110 - For left_padding in compute_metrics.py
Issue -
State: open - Opened by mrsempress 14 days ago
- 1 comment
#109 - [P1] Refactor ReftTrainer to save artifacts with the config
Issue -
State: open - Opened by BryanWBear 19 days ago
- 1 comment
Labels: enhancement, engineering
#108 - Fix: datasets.exceptions.DatasetNotFoundError when training with alpaca_data_cleaned
Pull Request -
State: closed - Opened by savadikarc 20 days ago
#107 - [P1] Experimental setup for instruction following experiments in the ReFT paper
Issue -
State: closed - Opened by savadikarc 20 days ago
- 3 comments
Labels: question
#106 - [P1] TypeError: Object of type type is not JSON serializable
Issue -
State: closed - Opened by ajayspatil7 21 days ago
- 4 comments
Labels: question
#105 - [P1] Possible to do batch inference?
Issue -
State: open - Opened by thistleknot 24 days ago
- 3 comments
Labels: question
#104 - [Major][pyreft-core] ReFT next release items
Issue -
State: open - Opened by frankaging 26 days ago
- 1 comment
Labels: enhancement, engineering
#103 - [P0] Revert back to ortho init as unstable training
Pull Request -
State: closed - Opened by frankaging 26 days ago
#102 - [P1] [Error] can not use bfloat16 and TypeError: Object of type type is not JSON serializable
Issue -
State: closed - Opened by mrsempress 26 days ago
- 21 comments
Labels: question
#101 - transformers_modules.microsoft.Phi-3-mini-4k-instruct.d269012bea6fbe38ce7752c8940fea010eea3383.modeling_phi3.Phi3ForCausalLM
Issue -
State: closed - Opened by thistleknot 28 days ago
- 1 comment
#100 - [Minor] Basic support of quantization
Pull Request -
State: closed - Opened by frankaging 28 days ago
#99 - [P1] Is it possible to merge the base model + REFT model into only model?
Issue -
State: closed - Opened by celsowm 29 days ago
- 1 comment
Labels: question
#98 - [P1] Loss decrease slow in readme demo when use NousResearch/Llama-2-7b-chat-hf
Issue -
State: closed - Opened by svjack 29 days ago
- 2 comments
Labels: question
#97 - [P0] Does this project support turning in 4bit or 8bit Quantify?
Issue -
State: closed - Opened by svjack 29 days ago
- 5 comments
Labels: enhancement, engineering
#96 - [P1] Multiple Positions Intervention
Issue -
State: closed - Opened by comeandcode 29 days ago
- 1 comment
Labels: question
#95 - [P1] Questions on differences between paper and code
Issue -
State: closed - Opened by calpt about 1 month ago
- 2 comments
Labels: question
#94 - [Minor] Enable lora with loreft training
Pull Request -
State: closed - Opened by frankaging about 1 month ago
#93 - [P1] support ReFT+PEFT by using ReftModel to wrap PeftModel (#46)
Pull Request -
State: closed - Opened by frankaging about 1 month ago
- 1 comment
#92 - [P1] Transitioning from peft to pyreft for Classification Approach
Issue -
State: open - Opened by SaBay89 about 1 month ago
- 2 comments
Labels: question
#91 - [P1] Model Compatibility
Issue -
State: closed - Opened by SaBay89 about 1 month ago
- 2 comments
Labels: question
#90 - forward() got an unexpected keyword argument 'unit_locations'
Issue -
State: closed - Opened by xerkey about 1 month ago
- 2 comments
#89 - Title: Fix: Shape Mismatch during Left Padding Adjustment in compute_metrics (Generated by Ana - AI SDE)
Pull Request -
State: closed - Opened by ana-ai-sde about 1 month ago
- 3 comments
#88 - [P1] Loreft example gsm8k train gives: RuntimeError: output with shape [64, 1, 7] doesn't match the broadcast shape [64, 0, 7]
Issue -
State: closed - Opened by jaymefosa about 2 months ago
- 3 comments
Labels: question
#87 - [P1] TypeError: train() takes 1 positional argument but 2 were given
Issue -
State: closed - Opened by alpozdarendeli about 2 months ago
- 1 comment
Labels: question
#86 - [P1] Loading REFT fro RoBERTa Models
Issue -
State: open - Opened by hSterz about 2 months ago
- 3 comments
Labels: question
#85 - [P0] Make `make_last_position_supervised_data_module` parallelizable to speed up processing!
Issue -
State: open - Opened by truskovskiyk about 2 months ago
- 2 comments
Labels: enhancement
#84 - [P1] Convert reft model to hf model
Issue -
State: closed - Opened by thu-yn about 2 months ago
- 1 comment
Labels: question
#83 - [P1] Getting error as IntervenableModel.train() takes 1 positional argument but 2 were given
Issue -
State: closed - Opened by atharvapatiil about 2 months ago
- 4 comments
Labels: question
#82 - [P0] Additional intervention arguments are not saved correctly, e.g. `add_bias`
Issue -
State: open - Opened by frankaging about 2 months ago
Labels: bug
#81 - [P1] How did you create the validation set for Commonsense reasoning hyperparameter tuning?
Issue -
State: closed - Opened by Edenzzzz about 2 months ago
- 5 comments
Labels: question
#80 - Getting issue while loading Phi3 in reft_model
Issue -
State: closed - Opened by atharvapatiil about 2 months ago
- 9 comments
#79 - [P1] RuntimeError: cutlassF: no kernel found to launch!
Issue -
State: closed - Opened by ds-praveenkumar about 2 months ago
- 4 comments
Labels: question
#78 - [P1] catastrophic forgetting
Issue -
State: closed - Opened by jiacheo about 2 months ago
- 1 comment
Labels: question
#77 - [P1] Intuitive-wise, should we keep the projection orthogonal during training?
Issue -
State: closed - Opened by Edenzzzz about 2 months ago
- 2 comments
Labels: question
#76 - ReFT + DPO Tutorial
Pull Request -
State: closed - Opened by AmirZur about 2 months ago
- 1 comment
#75 - [Minor] fix subspace (#72)
Pull Request -
State: closed - Opened by frankaging 2 months ago
- 1 comment
#74 - [Minor] More refactory to support Llama3 experiments
Pull Request -
State: closed - Opened by frankaging 2 months ago
#73 - [P1] Confirmation of alpaca_eval version
Issue -
State: closed - Opened by BaohaoLiao 2 months ago
- 4 comments
Labels: question
#72 - [P0] compreft.ipynb error = KeyError: 'subspaces'
Issue -
State: closed - Opened by RonanKMcGovern 2 months ago
- 4 comments
Labels: bug
#71 - [P1] Location of code for "LM training and serving with ReFT"
Issue -
State: open - Opened by RonanKMcGovern 2 months ago
- 2 comments
Labels: enhancement
#70 - [P2] Pyreft tensorboard integration
Issue -
State: open - Opened by PinetreePantry 2 months ago
Labels: bug
#69 - [P1] TypeError: Object of type type is not JSON serializable
Issue -
State: closed - Opened by srn-source 2 months ago
- 7 comments
Labels: question
#67 - [P0] Why is the number of trainable parameters for prefix-tuning is 0.11%
Issue -
State: closed - Opened by BaohaoLiao 2 months ago
- 7 comments
Labels: documentation, question
#66 - [P0] Adding DPO Support
Issue -
State: closed - Opened by jinzhuoran 2 months ago
- 8 comments
Labels: enhancement, help wanted
#65 - [P1] I am bit confused how to reproduce Table 2 (all baselines + main method)
Issue -
State: closed - Opened by sanyalsunny111 2 months ago
- 3 comments
Labels: question
#64 - [Major] Support Llama3 models
Pull Request -
State: closed - Opened by frankaging 2 months ago
#63 - [P1] TGI and vLLM support
Issue -
State: open - Opened by RonanKMcGovern 2 months ago
- 7 comments
Labels: question
#62 - [P1] MNLI has two validation set, how do you report the score
Issue -
State: closed - Opened by BaohaoLiao 2 months ago
- 3 comments
Labels: question
#61 - [P1] OpenAI CLIP model
Issue -
State: open - Opened by sailfish009 2 months ago
Labels: enhancement
#60 - [P1] How to attend to memorized intervention?
Issue -
State: open - Opened by chris-aeviator 2 months ago
- 2 comments
Labels: question
#59 - [P0] How do I train more than 1 layer at a time?
Issue -
State: closed - Opened by thistleknot 2 months ago
- 4 comments
Labels: enhancement
#58 - [P1] Error running new example code
Issue -
State: closed - Opened by dyahadila 2 months ago
- 2 comments
Labels: question
#57 - [Minor] Update README
Pull Request -
State: closed - Opened by frankaging 2 months ago
#56 - [Minor] Update README with Colab links.
Pull Request -
State: closed - Opened by frankaging 2 months ago
#55 - [Minor] Update README with an example.
Pull Request -
State: closed - Opened by frankaging 2 months ago
#54 - [P1] Is it possible to "bake in" ReFT changes to the weights and produce a model without pyreft dependencies?
Issue -
State: closed - Opened by ThaddeusChristopher 3 months ago
- 3 comments
Labels: question
#53 - [P1] Support for SeqtoSeq Models like M2M100
Issue -
State: closed - Opened by rumourscape 3 months ago
- 3 comments
Labels: enhancement
#52 - [P0] ReftGenerationDataset Error
Issue -
State: closed - Opened by PinetreePantry 3 months ago
- 5 comments
Labels: bug
#51 - [P0] Saving and reloading a ReftModel throws an error
Issue -
State: closed - Opened by PinetreePantry 3 months ago
- 13 comments
Labels: bug
#50 - [P1] Cannot reproduce instruction training
Issue -
State: closed - Opened by konstantina-ellalab 3 months ago
- 10 comments
Labels: question
#49 - Fix loading IntervenableModel for its subclasses
Pull Request -
State: closed - Opened by PinetreePantry 3 months ago
- 2 comments
#48 - Update chat_model.ipynb
Pull Request -
State: closed - Opened by Vikrant-Khedkar 3 months ago
#47 - Update README.md
Pull Request -
State: closed - Opened by Vikrant-Khedkar 3 months ago
- 2 comments
#46 - [P1] ReFT+PEFT by using ReftModel to wrap PeftModel
Issue -
State: closed - Opened by frankaging 3 months ago
- 2 comments
Labels: enhancement
#45 - [P0] reft_model loading as reft_model not as pyvene object
Issue -
State: closed - Opened by XiaoshuangJi 3 months ago
- 5 comments
Labels: bug
#44 - [Major] Zeta version
Pull Request -
State: closed - Opened by aryamanarora 3 months ago
- 4 comments
#43 - [P0] Simplify dataset structure
Issue -
State: closed - Opened by aryamanarora 3 months ago
- 2 comments
Labels: engineering
#42 - [P1] Question on arithmetic reasoning results
Issue -
State: closed - Opened by clarenceluo78 3 months ago
- 2 comments
Labels: question
#41 - [P1] Installing pyreft is stuck
Issue -
State: closed - Opened by konstantina-ellalab 3 months ago
- 10 comments
Labels: engineering
#40 - [P1] Is this repo support MPT architecture ? i got error
Issue -
State: closed - Opened by srn-source 3 months ago
- 7 comments
Labels: documentation, question
#39 - Fix GitHub links to standfordnlp in the README files
Pull Request -
State: closed - Opened by bbrowning 3 months ago
- 1 comment
#38 - [P0] Fixing the requirements for Kaggle and Google notebooks env
Pull Request -
State: closed - Opened by frankaging 3 months ago
#37 - [P0] Verify setup in Colab
Issue -
State: closed - Opened by aryamanarora 3 months ago
- 3 comments
Labels: bug, engineering
#36 - [P1] Compatibility with tooling that expects a HF transformer model
Issue -
State: open - Opened by chris-aeviator 3 months ago
- 3 comments
Labels: question
#35 - [P1] Lots of dependency issues.
Issue -
State: closed - Opened by Akshaysharma29 3 months ago
- 11 comments
Labels: question
#34 - evaluate
Issue -
State: closed - Opened by jeaneigsi 3 months ago
- 1 comment
#33 - [P0] LoReFT + Preference Pairs
Issue -
State: closed - Opened by frankaging 3 months ago
- 1 comment
Labels: enhancement
#32 - Update README.md
Pull Request -
State: closed - Opened by eltociear 3 months ago
#31 - TypeError: IntervenableModel.train() takes 1 positional argument but 2 were given
Issue -
State: closed - Opened by danikhan632 3 months ago
- 4 comments
#30 - [P1] QLoReFT
Issue -
State: closed - Opened by aryamanarora 3 months ago
- 1 comment
Labels: enhancement
#29 - [P0] data-loading script + fix data_dir bugs
Issue -
State: closed - Opened by aryamanarora 3 months ago
- 1 comment
#28 - [Pre-release] Renaming interventions
Issue -
State: closed - Opened by frankaging 3 months ago
#27 - [Pre-release] Releasing Llama-2 models mentioned in the paper
Issue -
State: closed - Opened by frankaging 3 months ago
#26 - [P0] Memory efficient version of LoReFT
Issue -
State: closed - Opened by frankaging 3 months ago
- 1 comment
Labels: enhancement
#25 - [P0] Multigpu and model sharding
Issue -
State: open - Opened by frankaging 3 months ago
- 2 comments
Labels: enhancement, help wanted
#24 - [Pre-release] Efficient intervention saving
Issue -
State: closed - Opened by frankaging 3 months ago
#23 - Verified README code, fix a bug preventing proper save and load
Pull Request -
State: closed - Opened by PinetreePantry 3 months ago
#22 - Update README.md
Pull Request -
State: closed - Opened by PinetreePantry 3 months ago
#21 - move generation args to config file
Pull Request -
State: closed - Opened by aryamanarora 4 months ago
#20 - minor fix
Pull Request -
State: closed - Opened by frankaging 4 months ago
#19 - Zen/gsm8k
Pull Request -
State: closed - Opened by frankaging 4 months ago
#18 - adjust decode stra
Pull Request -
State: closed - Opened by frankaging 4 months ago
#17 - add gd option
Pull Request -
State: closed - Opened by frankaging 4 months ago
#16 - more update on the padding thing with gsm8k and others
Pull Request -
State: closed - Opened by frankaging 4 months ago
#15 - fix padding on intervention locations
Pull Request -
State: closed - Opened by aryamanarora 4 months ago
#14 - [DO NOT MERGE] local shelve
Pull Request -
State: closed - Opened by frankaging 4 months ago
#13 - sharing interventions across positions
Pull Request -
State: closed - Opened by frankaging 4 months ago
#12 - gsm8k splits
Pull Request -
State: closed - Opened by aryamanarora 4 months ago
#11 - add an option for normalized input; GLUE in training HF eval
Pull Request -
State: closed - Opened by frankaging 4 months ago