doing something
@doing_something
713 subscribers
912 photos
36 videos
36 files
1.94K links
@smlkw doing something, just my notes to keep updates
Download Telegram
About
Blog
Apps
Platform
Join
doing something
713 subscribers
doing something
Forwarded from Hacker News
What Makes Code Hard to Read: Visual Patterns of Complexity (2023)
Article, Comments
seeinglogic blog
What Makes Code Hard To Read: Visual Patterns of Complexity
Not long ago, I was auditing a codebase for work (looking for bugs) when I realized that despite the quality of the code, I was becoming mentally fatigued extremely quickly and had a hard time working on it for long stretches of time…
105 views
doing something
Forwarded from Hacker News
AI-Generated Voice Evidence Poses Dangers in Court
Article, Comments
Default
AI-Generated Voice Evidence Poses Dangers in Court
In the age of AI, listener authentication of voice evidence should be permissive,  not mandatory.
109 views
doing something
https://github.com/fastplotlib/fastplotlib

#python
GitHub
GitHub - fastplotlib/fastplotlib: Next-gen fast plotting library running on WGPU using the pygfx rendering engine
Next-gen fast plotting library running on WGPU using the pygfx rendering engine - fastplotlib/fastplotlib
119 views
doing something
HF's ecosystem is insane

#ai
🤯1
122 views
doing something
Just a test to check EuroBERT tuning:

https://huggingface.co/ua-l/topics-classifier-EuroBERT-210m

#nlp #ai
huggingface.co
ua-l/topics-classifier-EuroBERT-210m · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
125 viewsedited  
doing something
https://huggingface.co/clapAI/modernBERT-base-multilingual-sentiment

#nlp
huggingface.co
clapAI/modernBERT-base-multilingual-sentiment · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
132 views
doing something
My experiments with topic dataset, now leader is ukr-models/xlm-roberta-base-uk

Model: https://huggingface.co/ua-l/topics-classifier-xlm-roberta-base-uk-v2

- Average accuracy: 0.6517
- Average F1 (MACRO): 0.4499

*without text pre-processing
🔥3
139 viewsedited  
doing something
#daily_ml_pain
138 views
doing something
😁4
148 views
doing something
Перші експерименти з навчанням ШІ на базі питань-відповідей сайту ua-lawyer.com/uk/ нейронної мережі від Google (Gemma 2, 9 млрд. параметрів).

Поки на прості питання відповідає, в законах плутається.
182 views
doing something
Forwarded from Hacker News
Gemma 3 Technical Report [pdf]
Article, Comments
143 views
doing something
doing something
Перші експерименти з навчанням ШІ на базі питань-відповідей сайту ua-lawyer.com/uk/ нейронної мережі від Google (Gemma 2, 9 млрд. параметрів). Поки на прості питання відповідає, в законах плутається.
gemma-2-2b-it fine-tuned on 10 epochs
137 views
doing something
#speech #ai
327 views
doing something
https://github.com/rohanprichard/fastrtc-demo how it looks like - https://www.youtube.com/watch?v=RjfurDYlpWA

#speech
GitHub
GitHub - rohanprichard/fastrtc-demo: A simple POC of FastRTC, a framework to use voice mode in python!
A simple POC of FastRTC, a framework to use voice mode in python! - rohanprichard/fastrtc-demo
133 views