mergekit
TextSnatcher
| mergekit | TextSnatcher | |
|---|---|---|
| 6 | 11 | |
| 3,521 | 1,213 | |
| 18.7% | - | |
| 9.2 | 2.8 | |
| 5 days ago | about 2 months ago | |
| Python | Vala | |
| GNU Lesser General Public License v3.0 only | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
mergekit
-
Language Models Are Super Mario: Absorbing Abilities from Homologous Models
For others like me who’d not heard of merging before, this seems to be one tool[0] (there may be others)
[0] https://github.com/arcee-ai/mergekit
- FLaNK AI Weekly 25 March 2025
- Tools for merging pretrained large language models
-
Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM
mergekit is the tool you need to do this
https://github.com/cg123/mergekit -
Iambe-RP-20b: An uncensored L2 Frankenstein model directly trained with RP-oriented cDPO
I actually asked the creator of mergekit a question here. In his response, I learned how to use task_arithmetic to isolate the deltas. One could, in theory, use WANDA on that model from the second example, then merge it back into another model. However, that's firmly past the frontier of what has been tried, so experimentation might be messy.
-
LLMs cannot find reasoning errors, but can correct them
Ah, actually reviewing that more closely I found a link to it in the acknowledgements.
https://github.com/cg123/mergekit
TextSnatcher
- FLaNK AI Weekly 25 March 2025
- TextSnatcher: Copy text from images, for the Linux Desktop
-
Blog(ish): So I switched to Arch for a month...
- https://github.com/RajSolai/TextSnatcher
- TextSnatcher: How to Copy Text from Images? Perform OCR operations in seconds on Linux Desktop.
-
What are you working on [July 2022]
Thanks to Gtk4 support and packages available on macOS via homebrew. Today I was successful able to build .app for the app. You can track the progress here https://github.com/RajSolai/TextSnatcher branch 'macos-dev'
- I made a desktop popup dictionary for games and apps. It shows definitions on hover and allows you to create Anki cards.
- If you want to OCR your PDF, the fastest, easiest and less buggy tool out there is "pdfsandwich"
- TextSnatcher – An Easy to use OCR front end for GNU/Linux
- Copy Text from Images to Your Clipboard
-
How can I do an OCR scan of a PDF that has human handwriting text?
You can do this from a desktop app like https://github.com/RajSolai/TextSnatcher
What are some alternatives?
Finetune_LLMs - Repo for fine-tuning Casual LLMs
normcap - OCR powered screen-capture tool to capture information instead of images
xTuring - Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6
tesseract-ocr - Tesseract Open Source OCR Engine (main repository)
LLMLingua - To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
PaddleOCR - Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
task_vectors - Editing Models with Task Arithmetic
OCRmyPDF - OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
difftastic - a structural diff that understands syntax 🟥🟩
nixpkgs-mozilla - Mozilla overlay for Nixpkgs.
makeMoE - From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
GameHub - All your games in one place