e-p-armstrong/augmentoolkit

Create Custom LLMs

Stars: 1.9k
Forks: 248
Open beginner issues: 0
Indexed issues: 26

Dominant language: Python
License: MIT
Last GitHub push: Jun 27, 2026
Latest indexed: Sep 15, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: good first issue
PR merge metrics: No merged PRs in 30d

Open All

26 open issues indexed

Enhancement — Adding GPU support to classifier training Open

enhancement good first issue

e-p-armstrong/augmentoolkit#35 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026
Master list and simplified data are not being saved. Open

e-p-armstrong/augmentoolkit#38 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
List index out of range error Open

e-p-armstrong/augmentoolkit#46 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Can the answers be answered in another language? Open

e-p-armstrong/augmentoolkit#47 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
index out of range (between phase 1 and phase 2) Open

e-p-armstrong/augmentoolkit#51 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Google Colab Integration for Augmentoolkit Open

e-p-armstrong/augmentoolkit#53 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Traceback RE SE_GUTENBERG = config["SCRAPING"]["USE_GUTENBERG"] Open

e-p-armstrong/augmentoolkit#56 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Feature Request: Support multiple BASE_URLs in original pipeline Open

e-p-armstrong/augmentoolkit#60 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
First input file is the only one processed Open

e-p-armstrong/augmentoolkit#61 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
USE_FILENAMES option is broken Open

e-p-armstrong/augmentoolkit#68 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Create a chunk summary and discarting irrevelant information. Open

enhancement

e-p-armstrong/augmentoolkit#71 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Random Data in Outputs Open

e-p-armstrong/augmentoolkit#73 · 3 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026
UnicodeDecodeError: 'charmap' codec can't decode byte 0x98 in position 2574: character maps to <undefined> Open

e-p-armstrong/augmentoolkit#74 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Can we specify the language for generating content, such as French, German, Chinese, etc Open

e-p-armstrong/augmentoolkit#76 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Successful Run But No Stories Generated! Open

e-p-armstrong/augmentoolkit#84 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
subprocess.run([sys.executable, "processing.py"], cwd=folder_path, env=env, check=True) 多线程报错 Open

e-p-armstrong/augmentoolkit#85 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Communication between chunks/paragraphs Open

e-p-armstrong/augmentoolkit#92 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Error with Phase 2: 'NoneType' object is not subscriptable Open

e-p-armstrong/augmentoolkit#93 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Support Generating CoT SFT Data Using DeepSeek R1 Open

e-p-armstrong/augmentoolkit#94 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Trying to convert a logging directory to a dataset, when that directory does not exist! Open

e-p-armstrong/augmentoolkit#95 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
AttributeError: 'NoneType' object has no attribute 'group' Open

e-p-armstrong/augmentoolkit#96 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
factual_datagen_full() missing 150 required positional arguments Open

e-p-armstrong/augmentoolkit#101 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Invalid references to split(x) [0] or [1] before testing if string value contains x Open

e-p-armstrong/augmentoolkit#108 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
cant start local - openai.APIConnectionError: Connection error Open

e-p-armstrong/augmentoolkit#114 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
MultiSource Recall hang due to regex catastrophic backtracking Open

e-p-armstrong/augmentoolkit#116 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Assistance required. Cannot load local .gguf model or run revised .yaml config files. Open

e-p-armstrong/augmentoolkit#117 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

A short digest of beginner-friendly GitHub issues.