Comments (4)
Thanks @Green-Sky for your attention and helpful feedback.
had to manually checkout your master.
Unfortunately, this is because ggerganov/ggml#254 has not been merged yet. I'll checkout upstream master once it's merged. Maybe I can request Georgi's attention in that PR.
i got a better model
Thanks for trying this. It was also in my mind to try Laion's models, and seems that your modification sould work for both cases. I'll test it and modify the script to handle models from both sources.
hardcoded paths in examples/main
Sorry for that, I'm a little bit lazy to pass them from command line every time I'm running during the development ๐ถโ๐ซ๏ธ The next commit today will remove them and parse them from command line instead.
I'll also share examples for zero-shot image labelling (one image vs. multiple texts), and semantic image search (multiple images vs. one textual query).
from clip.cpp.
Got it. Fixed it now.
Also removed hardcoded stuff from the example and it reads from the command line. Run ./bin/main -h
for options.
Later today or tomorrow, I'll update the conversion script to handle models from Laion and craft better examples.
Please feel free to continue sharing your feedback, highly appreciated.
from clip.cpp.
had to manually checkout your master.
Unfortunately, this is because ggerganov/ggml#254 has not been merged yet. I'll checkout upstream master once it's merged. Maybe I can request Georgi's attention in that PR.
What I meant is that the commit should be one in your fork (for the pr). But even github cant find the exact commit, which means you never pushed the committed commit.
from clip.cpp.
closing this as done :)
from clip.cpp.
Related Issues (20)
- Support image-only HOT 8
- Typo in the error message HOT 1
- Can this use convNeXt architecture? HOT 4
- Prepare clip.cpp for upcoming llava.cpp HOT 1
- Support custom mean-std normalization HOT 3
- not enough space in the context's memory pool (on Apple M1 Max, 32GB RAM, clip-vit-b-32) HOT 6
- Provide Python bindings
- [ZSL] Results doesn't match hugging face demo HOT 5
- Segmentation Fault and Core Dump when running image-search-build with Multiple images in folder Using the 4bit model HOT 5
- Can the text-encoder / vision-encoder be optional rather than mandatory? HOT 2
- Publish as a Pip-installable Python package HOT 1
- Improve zero-shot labeling
- python binding: OSError libggml.so: cannot open shared object file HOT 4
- Migrate to GGUF HOT 4
- Move ZSL implementation to `clip` lib as a function
- Support downloading models in Python bindings HOT 1
- Introduce Java bindings
- Support batch inference for models other than patch32 HOT 3
- python bindings๐: Support for accepting list of Input in the encoding methods HOT 7
- Implement bicubic interpolation
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from clip.cpp.