[OSPP]: Personalized LLM Agent based on KubeEdge-Ianvs Cloud-Edge Collaboration #154

Frank-lilinjie · 2024-09-29T10:49:40Z

The PR of Personalized LLM Agent based on KubeEdge-Ianvs Cloud-Edge Collaboration

MooreZheng

There are CI issues that needs to be resolved

Run pylint '/home/runner/work/ianvs/ianvs/core'
************* Module core.testcasecontroller.algorithm.paradigm.singletask_learning.singletask_learning_active_boost
core/testcasecontroller/algorithm/paradigm/singletask_learning/singletask_learning_active_boost.py:66:4: R09[1](https://github.com/kubeedge/ianvs/actions/runs/11092223886/job/30816995965?pr=154#step:5:1)7: Too many positional arguments (7/5) (too-many-positional-arguments)
************* Module core.testenvmanager.dataset.dataset
core/testenvmanager/dataset/dataset.py:119:4: R091[7](https://github.com/kubeedge/ianvs/actions/runs/11092223886/job/30816995965?pr=154#step:5:8): Too many positional arguments (8/5) (too-many-positional-arguments)
core/testenvmanager/dataset/dataset.py:206:4: R0917: Too many positional arguments (6/5) (too-many-positional-arguments)
core/testenvmanager/dataset/dataset.py:213:4: R0917: Too many positional arguments (7/5) (too-many-positional-arguments)
core/testenvmanager/dataset/dataset.py:246:4: R0917: Too many positional arguments (7/5) (too-many-positional-arguments)
core/testenvmanager/dataset/dataset.py:2[8](https://github.com/kubeedge/ianvs/actions/runs/11092223886/job/30816995965?pr=154#step:5:9)5:4: R0917: Too many positional arguments (7/5) (too-many-positional-arguments)
core/testenvmanager/dataset/dataset.py:329:4: R0917: Too many positional arguments (7/5) (too-many-positional-arguments)
core/testenvmanager/dataset/dataset.py:368:4: R0[9](https://github.com/kubeedge/ianvs/actions/runs/11092223886/job/30816995965?pr=154#step:5:10)17: Too many positional arguments (6/5) (too-many-positional-arguments)

-----------------------------------
Your code has been rated at 9.95/[10](https://github.com/kubeedge/ianvs/actions/runs/11092223886/job/30816995965?pr=154#step:5:11)

Error: Process completed with exit code 8.

MooreZheng · 2024-10-22T16:15:41Z

/lgtm

hsj576

/lgtm

MooreZheng

To facilitate international impacts, need to translate Chinese comments into English for load_json and preprocess of basemodel.py.

MooreZheng · 2024-10-26T03:06:47Z

examples/llm-agent/singletask_learning_bench/testalgorithms/basemodel.py

+        pass
+
+    def load_json(self, data_dir, tokenizer, token_factor = 32):
+        MYjson=datasets.load_dataset("json",data_files=data_dir) # 加载Json数据集


For load_json of basemodel.py, need to translate Chinese comments into English to facilitate international impacts

MooreZheng · 2024-10-26T03:07:53Z

examples/llm-agent/singletask_learning_bench/testalgorithms/basemodel.py

+
+
+    def preprocess(self, samples, MAX_LENGTH, tokenizer):
+        input_ids,attention_mask,labels=[],[],[] # 初始化三个空列表


For preprocess of basemodel.py, need to translate Chinese comments into English

MooreZheng

Just to remind @Frank-lilinjie : Chinese statements need to be refined into English before merging.

Besides, this pull request contains 15 commits, which might make maintenance difficult, considering the number of contributors, pull requests, and their commits in KubeEdge Ianvs recently. In the final stage, @Frank-lilinjie can squash the commits into one using rebase techniques.

Frank-lilinjie · 2024-10-29T02:11:46Z

Just to remind @Frank-lilinjie : Chinese statements need to be refined into English before merging.

Besides, this pull request contains 15 commits, which might make maintenance difficult, considering the number of contributors, pull requests, and their commits in KubeEdge Ianvs recently. In the final stage, @Frank-lilinjie can squash the commits into one using rebase techniques.

copy that

MooreZheng

Need to change print using loggers

hsj576

The "print" should be removed or replaced by "LOGGER.info".

hsj576 · 2024-10-31T02:37:39Z

examples/llm-agent/singletask_learning_bench/testenv/rouge.py

+    return rougeL
+
+def calculate_mean(lst):
+    print(lst)


The "print" should be removed or replaced by "LOGGER.info".

hsj576

/lgtm

MooreZheng

This pull request contains 20 commits, which might make maintenance difficult, considering the number of contributors, pull requests, and their commits in KubeEdge Ianvs recently. In the final stage, @Frank-lilinjie can squash the commits into one using rebase techniques.

Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn> delete proposal in this branch Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn> fix: deprecate outdated interface of pandas Signed-off-by: Yu Fan <fany@buaa.edu.cn> fix: pylint R0917 error Signed-off-by: Yu Fan <fany@buaa.edu.cn> fix the issuse of Chinese comments Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn> parent 5fd70d2 author Frank-lilinjie <lilinjie@bupt.edu.cn> 1730356419 +0800 committer Frank-lilinjie <lilinjie@bupt.edu.cn> 1730365262 +0800 parent 5fd70d2 author Frank-lilinjie <lilinjie@bupt.edu.cn> 1730356419 +0800 committer Frank-lilinjie <lilinjie@bupt.edu.cn> 1730365240 +0800 Print replaced with logging Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn> add a proposal of Smart Coding benchmark suite Signed-off-by: boX <442572328@qq.com> update and improve the proposal Improve the architecture diagram Signed-off-by: boX <442572328@qq.com> update and improve the proposal Signed-off-by: boX <442572328@qq.com> add Proposal for Large Language Model Edge Benchmark Suite: Implementation on KubeEdge-lanvs Signed-off-by: yexiaochuan <tap91624@gmail.com> add Proposal for Large Language Model Edge Benchmark Suite: Implementation on KubeEdge-lanvs Signed-off-by: yexiaochuan <yxc2020@foxmail.com> llm suite benchmark implement Signed-off-by: yexiaochuan <yxc2020@foxmail.com> Revert "llm suite benchmark implement" This reverts commit f341b0f. Signed-off-by: yexiaochuan <yxc2020@foxmail.com> Fix llm edge benchmark suite description and highlight edge in the name of the documents Signed-off-by: yexiaochuan <yxc2020@foxmail.com> fix pylint 3.9 too-many-positional-arguments Signed-off-by: yexiaochuan <yxc2020@foxmail.com> Trigger CI Signed-off-by: yexiaochuan <yxc2020@foxmail.com> Trigger CI Signed-off-by: yexiaochuan <yxc2020@foxmail.com> Fix pylint disable R0913 Signed-off-by: yexiaochuan <yxc2020@foxmail.com> Fix pylint disable R0917 Signed-off-by: yexiaochuan <yxc2020@foxmail.com> Revert: Remove extra pylint fix changes Signed-off-by: yexiaochuan <yxc2020@foxmail.com> chore: Empty commit to trigger CI Signed-off-by: yexiaochuan <yxc2020@foxmail.com> add: Heterogeneous Multi-Edge Collaborative Neural Network Inference for High Mobility Scenarios: Base on KubeEdge-Ianvs proposal Signed-off-by: wyoung1 <wyoung@mail.ustc.edu.cn> coding for ospp Signed-off-by: wyoung1 <wyoung@mail.ustc.edu.cn> fix pylint Signed-off-by: wyoung1 <wyoung@mail.ustc.edu.cn> fix pylint issue Signed-off-by: wyoung1 <wyoung@mail.ustc.edu.cn> add: add a simple demo of feadereated learning in ianvs Signed-off-by: Marchons <d12863606746@outlook.com> Signed-off-by: Marchons <1286360646@qq.com> Revert "OSPP: Development of Federated Incremental Learning for Label Scarcity: Base on KubeEdge-Ianvs" Revert "Merge pull request kubeedge#160 from kubeedge/revert-143-dev_script" This reverts commit 4f01ee5, reversing changes made to 9553051. Signed-off-by: Marchons <1286360646@qq.com> add Impl for llm edge benchmark suite Signed-off-by: yexiaochuan <yxc2020@foxmail.com> adapt Impl in core for llm edge benchmark suite Signed-off-by: yexiaochuan <yxc2020@foxmail.com> Fix impl on singletast_learning with compression Signed-off-by: yexiaochuan <yxc2020@foxmail.com> chore: trigger CI Signed-off-by: yexiaochuan <yxc2020@foxmail.com> CI: fix pylint warnings Signed-off-by: yexiaochuan <yxc2020@foxmail.com> CI: fix pylint warnings Signed-off-by: yexiaochuan <yxc2020@foxmail.com> fix: update comments and configuration parameters Signed-off-by: yexiaochuan <yxc2020@foxmail.com> fix core of dataset Signed-off-by: Frank-lilinjie <lilinjie@bupt.edu.cn>

MooreZheng · 2024-10-31T10:29:27Z

/lgtm

MooreZheng · 2024-10-31T10:30:21Z

/approve

MooreZheng

All concerns are tackled. Well done! @Frank-lilinjie

kubeedge-bot · 2024-10-31T10:31:16Z

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: hsj576, MooreZheng

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

~~OWNERS~~ [MooreZheng]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

kubeedge-bot requested review from MooreZheng and Poorunga September 29, 2024 10:49

kubeedge-bot added the size/L Denotes a PR that changes 100-499 lines, ignoring generated files. label Sep 29, 2024

MooreZheng requested review from hsj576 and removed request for Poorunga October 14, 2024 02:51

MooreZheng requested changes Oct 14, 2024

View reviewed changes

kubeedge-bot assigned MooreZheng Oct 14, 2024

MooreZheng assigned hsj576 and Frank-lilinjie Oct 14, 2024

kubeedge-bot added the lgtm Indicates that a PR is ready to be merged. label Oct 22, 2024

hsj576 approved these changes Oct 26, 2024

View reviewed changes

MooreZheng requested changes Oct 26, 2024

View reviewed changes

kubeedge-bot removed the lgtm Indicates that a PR is ready to be merged. label Oct 26, 2024

MooreZheng requested changes Oct 28, 2024

View reviewed changes

Frank-lilinjie requested review from MooreZheng and hsj576 October 30, 2024 08:19

MooreZheng requested changes Oct 30, 2024

View reviewed changes

FuryMartin mentioned this pull request Oct 30, 2024

OSPP: Cloud-edge collaborative inference for LLM based on KubeEdge-Ianvs #149

Merged

hsj576 suggested changes Oct 31, 2024

View reviewed changes

Frank-lilinjie requested review from MooreZheng and hsj576 October 31, 2024 06:36

hsj576 approved these changes Oct 31, 2024

View reviewed changes

kubeedge-bot added the lgtm Indicates that a PR is ready to be merged. label Oct 31, 2024

MooreZheng requested changes Oct 31, 2024

View reviewed changes

kubeedge-bot added size/XL Denotes a PR that changes 500-999 lines, ignoring generated files. and removed lgtm Indicates that a PR is ready to be merged. size/L Denotes a PR that changes 100-499 lines, ignoring generated files. labels Oct 31, 2024

Frank-lilinjie force-pushed the LLMagent branch from 5f4669b to ce35e8d Compare October 31, 2024 09:30

Frank-lilinjie force-pushed the LLMagent branch from 896156e to 7829adf Compare October 31, 2024 10:03

kubeedge-bot added the lgtm Indicates that a PR is ready to be merged. label Oct 31, 2024

kubeedge-bot added the approved Indicates a PR has been approved by an approver from all required OWNERS files. label Oct 31, 2024

MooreZheng approved these changes Oct 31, 2024

View reviewed changes

kubeedge-bot merged commit f424d35 into kubeedge:main Oct 31, 2024
13 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[OSPP]: Personalized LLM Agent based on KubeEdge-Ianvs Cloud-Edge Collaboration #154

[OSPP]: Personalized LLM Agent based on KubeEdge-Ianvs Cloud-Edge Collaboration #154

Frank-lilinjie commented Sep 29, 2024

MooreZheng left a comment •

edited

Loading

MooreZheng commented Oct 22, 2024

hsj576 left a comment

MooreZheng left a comment

MooreZheng Oct 26, 2024

MooreZheng Oct 26, 2024

MooreZheng left a comment

Frank-lilinjie commented Oct 29, 2024

MooreZheng left a comment

hsj576 left a comment

hsj576 Oct 31, 2024

Frank-lilinjie Oct 31, 2024

hsj576 left a comment

MooreZheng left a comment

MooreZheng commented Oct 31, 2024

MooreZheng commented Oct 31, 2024

MooreZheng left a comment

kubeedge-bot commented Oct 31, 2024



		def preprocess(self, samples, MAX_LENGTH, tokenizer):
		input_ids,attention_mask,labels=[],[],[] # 初始化三个空列表

[OSPP]: Personalized LLM Agent based on KubeEdge-Ianvs Cloud-Edge Collaboration #154

[OSPP]: Personalized LLM Agent based on KubeEdge-Ianvs Cloud-Edge Collaboration #154

Conversation

Frank-lilinjie commented Sep 29, 2024

MooreZheng left a comment • edited Loading

Choose a reason for hiding this comment

MooreZheng commented Oct 22, 2024

hsj576 left a comment

Choose a reason for hiding this comment

MooreZheng left a comment

Choose a reason for hiding this comment

MooreZheng Oct 26, 2024

Choose a reason for hiding this comment

MooreZheng Oct 26, 2024

Choose a reason for hiding this comment

MooreZheng left a comment

Choose a reason for hiding this comment

Frank-lilinjie commented Oct 29, 2024

MooreZheng left a comment

Choose a reason for hiding this comment

hsj576 left a comment

Choose a reason for hiding this comment

hsj576 Oct 31, 2024

Choose a reason for hiding this comment

Frank-lilinjie Oct 31, 2024

Choose a reason for hiding this comment

hsj576 left a comment

Choose a reason for hiding this comment

MooreZheng left a comment

Choose a reason for hiding this comment

MooreZheng commented Oct 31, 2024

MooreZheng commented Oct 31, 2024

MooreZheng left a comment

Choose a reason for hiding this comment

kubeedge-bot commented Oct 31, 2024

MooreZheng left a comment •

edited

Loading