Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / mingkaid/rl-prompt issues and pull requests

#45 - Repeating tokens in optimized prompt

Issue - State: open - Opened by AMJasser 5 months ago

#44 - Add __init__.py to make rlprompt importable

Pull Request - State: open - Opened by AMJasser 5 months ago

#43 - Can we use this as a layer between user and RAG model?

Issue - State: open - Opened by deepakdev1507 9 months ago - 1 comment

#42 - seems have a bug in evaluate function

Issue - State: open - Opened by A11en0 11 months ago - 1 comment

#41 - Questions on the Gradients of LLM

Issue - State: open - Opened by Schwartz-Zha 11 months ago

#40 - Baselines results

Issue - State: open - Opened by Davido111200 almost 1 year ago

#39 - Why does this method need so much steps?

Issue - State: closed - Opened by A11en0 about 1 year ago - 2 comments

#38 - Reproducibility and randomness

Issue - State: closed - Opened by YasamanJafari about 1 year ago - 1 comment

#37 - BrokenPipeError: [Errno 32] Broken pipe

Issue - State: closed - Opened by Xinhui-Zhu about 1 year ago - 2 comments

#36 - question: Is the model used in the policy network always distilgpt?

Issue - State: closed - Opened by pascalhuszar about 1 year ago - 3 comments

#35 - About the prepended special character \u0120.

Issue - State: closed - Opened by guozix about 1 year ago - 3 comments

#34 - About the RL training

Issue - State: closed - Opened by FayeXXX about 1 year ago - 3 comments

#33 - Train using vertexai

Issue - State: closed - Opened by yguezpa about 1 year ago - 1 comment

#32 - Network is unreachable

Issue - State: closed - Opened by rabi-fei over 1 year ago - 1 comment

#31 - question

Issue - State: closed - Opened by 18712234451 over 1 year ago - 2 comments

#30 - CUDA Out of Memory training on shakespeare dataset

Issue - State: closed - Opened by DwyaneLQY over 1 year ago - 2 comments

#29 - A question about ppl score

Issue - State: closed - Opened by FayeXXX over 1 year ago - 7 comments

#28 - Clarification on the RL problem

Issue - State: closed - Opened by hv68 over 1 year ago - 1 comment

#27 - classification with gpt & training time

Issue - State: closed - Opened by MatthewCYM over 1 year ago - 2 comments

#26 - classifcation with gpt

Issue - State: closed - Opened by MatthewCYM over 1 year ago - 2 comments

#25 - RL-prompt MLP loss

Issue - State: closed - Opened by hv68 over 1 year ago - 1 comment

#24 - Scope of this project

Issue - State: closed - Opened by YujingYang666777 over 1 year ago - 2 comments

#23 - An error about Hydra when running examples/few-shot-classification

Issue - State: closed - Opened by plusnli over 1 year ago - 7 comments

#22 - A question about prompt initialization

Issue - State: closed - Opened by beeevita over 1 year ago - 3 comments

#21 - ImportError

Issue - State: closed - Opened by beeevita over 1 year ago - 2 comments

#20 - Add outputs

Pull Request - State: closed - Opened by mingkaid over 1 year ago

#19 - Add TST outputs

Pull Request - State: closed - Opened by mingkaid over 1 year ago

#18 - output data of your experiment

Issue - State: closed - Opened by li-jing-wen over 1 year ago - 4 comments

#17 - question about using greedy search during inference

Issue - State: closed - Opened by lihenglin over 1 year ago - 1 comment

#16 - Fix errors with irregular batch sizes during inferences

Pull Request - State: closed - Opened by mingkaid over 1 year ago

#15 - assert len(prompt_strs) == len(source_strs) fails during inference

Issue - State: closed - Opened by mahdiabdollahpour almost 2 years ago - 4 comments

#14 - CVE-2007-4559 Patch

Pull Request - State: closed - Opened by TrellixVulnTeam almost 2 years ago

#13 - Transferring Prompts across LMs

Issue - State: closed - Opened by 52ie about 2 years ago - 3 comments

#11 - Cls update

Pull Request - State: closed - Opened by MM-IR about 2 years ago

#10 - some Doubts about a symbol

Issue - State: closed - Opened by oujieww about 2 years ago - 2 comments

#9 - Could RLPROMPT be applied to zero-shot settings?

Issue - State: closed - Opened by shadowkiller33 about 2 years ago - 5 comments

#8 - RuntimeError

Issue - State: closed - Opened by Ericmututu about 2 years ago - 2 comments

#7 - Revamp code structure

Pull Request - State: closed - Opened by mingkaid about 2 years ago

#6 - Lack of evaluation in `modular-interface` branch

Issue - State: closed - Opened by Dinxin about 2 years ago - 4 comments

#5 - Could not find the exact place where the training set is input?

Issue - State: closed - Opened by Dinxin about 2 years ago - 4 comments

#4 - The data in 'data/prompt-gpt2-vocab' folder seems meaningless?

Issue - State: closed - Opened by Dinxin about 2 years ago - 1 comment

#3 - generate_prompts.py may be only usable for `input_specific=True` option?

Issue - State: closed - Opened by Dinxin about 2 years ago - 1 comment

#2 - Test cls

Pull Request - State: closed - Opened by MM-IR over 2 years ago

#1 - Add clean research code

Pull Request - State: closed - Opened by mingkaid over 2 years ago