Product crafting...
The full day of modernizing the code base
Looked at the number of issues closed, in total more than 1k commits in both repos
#product
The full day of modernizing the code base
Looked at the number of issues closed, in total more than 1k commits in both repos
#product
When I work with audio and some checks don't work, then again old way to understand:
https://stackoverflow.com/questions/67598056/what-is-the-difference-between-content-type-eg-audio-vnd-wave-audio-wav
#daily_pain
https://stackoverflow.com/questions/67598056/what-is-the-difference-between-content-type-eg-audio-vnd-wave-audio-wav
#daily_pain
Stack Overflow
What is the difference between content type eg: "audio/vnd.wave" / "audio/wav"
There are a lot of content types like:
1. "audio/vnd.wave" / "audio/wav" / "audio/x-wav"
2. "video/avi" / "video/x-avi"
3. "audio/amr" /...
1. "audio/vnd.wave" / "audio/wav" / "audio/x-wav"
2. "video/avi" / "video/x-avi"
3. "audio/amr" /...
https://youtu.be/DPbdzudU8Eg?feature=shared
З відео:
#video
З відео:
Більшість статей в наукові журнали не публікуються, бо їх можна зрозуміти. Публікуються ті, які не можна.
#video
YouTube
Этот правый левый мир
Советский научно-популярный фильм о симметрии в нашем мире. По мотивам книги М. Гарднера.
Центрнаучфильм, 1971
Авторы сценария: С.Райтбурт, В.Шрейберг
режиссер: С.Райтбург.
В ролях: д.т.н. проф.В.Шестаков
Центрнаучфильм, 1971
Авторы сценария: С.Райтбурт, В.Шрейберг
режиссер: С.Райтбург.
В ролях: д.т.н. проф.В.Шестаков
doing something
Seems like I need to test Robyn again This feature is support useful when I do APIs with FastAPI But using Rust-powered Python web framework looks pretty tempting #python #rust
https://github.com/sparckles/Robyn
A link to this Robyn
Also, another feature I like - we can eliminate an ASGI/WSGI proxy server when running the API
A link to this Robyn
Also, another feature I like - we can eliminate an ASGI/WSGI proxy server when running the API
GitHub
GitHub - sparckles/Robyn: Robyn is a Super Fast Async Python Web Framework with a Rust runtime.
Robyn is a Super Fast Async Python Web Framework with a Rust runtime. - sparckles/Robyn
MamayLM-Gemma-2-9B-IT-v0.1:
- transformers: https://colab.research.google.com/drive/1XAECWGFyMsgYeidF7XhHW7U-_LsdQSkB?usp=sharing
- vllm: https://colab.research.google.com/drive/1QC-qfesfRrOXJlJmkO0bGj9EwHfg8uSQ?usp=sharing
- llama-cpp: https://colab.research.google.com/drive/1dygCGRrPoWS670ICBB2o3QIF1SvH9lKU?usp=sharing
#nlp #ai
- transformers: https://colab.research.google.com/drive/1XAECWGFyMsgYeidF7XhHW7U-_LsdQSkB?usp=sharing
- vllm: https://colab.research.google.com/drive/1QC-qfesfRrOXJlJmkO0bGj9EwHfg8uSQ?usp=sharing
- llama-cpp: https://colab.research.google.com/drive/1dygCGRrPoWS670ICBB2o3QIF1SvH9lKU?usp=sharing
#nlp #ai
Google
MamayLM - a quick test on instruction-tuned model.ipynb
Colab notebook
👍1🔥1
doing something
MamayLM-Gemma-2-9B-IT-v0.1: - transformers: https://colab.research.google.com/drive/1XAECWGFyMsgYeidF7XhHW7U-_LsdQSkB?usp=sharing - vllm: https://colab.research.google.com/drive/1QC-qfesfRrOXJlJmkO0bGj9EwHfg8uSQ?usp=sharing - llama-cpp: https://colab.r…
Made a colab to show how we can use MamayLM with GLiNER model to solve the PII detection task for Ukrainian.
In test cases, only one sample GLiNER could not successfully recognize, but after English translation - it does.
So, the algorithm is simple:
- Translate Ukrainian sentence to English
- Load GLiNER model that is zero-shot NER model
- Pass translated sentences and detect PII entities
Instead of MamayLM, we can use MADLAD models or other NMT models.
Colab: https://colab.research.google.com/drive/1P3jBiixz0Mv31NF6cc6K3wG5HtOW_eL9?usp=sharing
#ai #pii #nlp #security
In test cases, only one sample GLiNER could not successfully recognize, but after English translation - it does.
So, the algorithm is simple:
- Translate Ukrainian sentence to English
- Load GLiNER model that is zero-shot NER model
- Pass translated sentences and detect PII entities
Instead of MamayLM, we can use MADLAD models or other NMT models.
Colab: https://colab.research.google.com/drive/1P3jBiixz0Mv31NF6cc6K3wG5HtOW_eL9?usp=sharing
#ai #pii #nlp #security
🔥3
Forwarded from Ihor Stepanov
You can reduce the translation step right now thanks to this: https://huggingface.co/knowledgator/gliner-x-large-v0.5
Ihor Stepanov
You can reduce the translation step right now thanks to this: https://huggingface.co/knowledgator/gliner-x-large-v0.5
Only one sample was not processed correctly with knowledgator/gliner-x-large-v0.5
But the model is more efficient than previous solution with MamayLM + GLiNER
Colab: https://colab.research.google.com/drive/1tP2gNfvgzscaGKQNkQ0AqBQGSKW6ZUis?usp=sharing
#ai #nlp #pii #security
But the model is more efficient than previous solution with MamayLM + GLiNER
Colab: https://colab.research.google.com/drive/1tP2gNfvgzscaGKQNkQ0AqBQGSKW6ZUis?usp=sharing
#ai #nlp #pii #security
👍2