Downside: rough around the edges. Bumpy learning curve. Upside: absolutely no chance of being bought and ruined by a narcissistic billionaire Until a week ago I thought the downsides outweighed the upsides – I have now been convinced otherwise!
OPEN SOURCE
-
Learn Declarative ML: Build Models in 15 Lines of Code
By
–
Want to learn about declarative #ML? Join our webinar with @devvret_rishi
, cofounder at @predibase
, to learn:
– About declarative ML systems incl. open-source http://
Ludwig.ai from @Uber – How to build & deploy ML/DL models in <15 lines of code https://
pbase.ai/3Ticrpz -
LangChain 0.0.9: Hugging Face Embeddings and API Key Management
By
–
LangChain version 0.0.9 Support for embeddings with @huggingface through `sentence_transformers` from @abdrahman_issam (example notebook: https://colab.research.google.com/drive/1lbjO0-nITa5c8RXfagsIZDqxZ_mVl_2k?usp=sharing…) Better support for different ways of specifying API keys from @camjuu
-
YOLOv7 Pose: Single-Stage Multi-Person Keypoint Detection
By
–
Unlike conventional Pose Estimation algorithms, YOLOv7 pose is a single-stage multi-person keypoint detector. It is similar to the bottom-up approach but heatmap free. It is an extension of the one-shot pose detector – YOLO-Pose. https://
learnopencv.com/yolov7-pose-vs
-mediapipe-in-human-pose-estimation/
…
#yolov7 #poseestimation -
Andrew’s Takahe Project Development Gains Excitement
By
–
I'm excited about the one Andrew is building at the moment – haven't looked for any others yet though https://
github.com/andrewgodwin/t
akahe
… -
NLLB-200 Achieves Lowest Content Deletion Rate Among Translation Services
By
–
NLLB-200 sees only 0.13% of translated content deleted. That’s the lowest percentage across all machine translation services available on the platform, suggesting that the resulting translations are being understood & accepted. 3/5
-
NLLB-200 Achieves Superior Translation Quality Across All Languages
By
–
Across all languages, NLLB-200 is seeing the best results for translations modified <10% compared to all other MT services on the platform — a strong signal for the quality of translations that are being generated. 4/5
-
NLLB-200 becomes third most-used translation engine in four months
By
–
NLLB-200 now represents 3.8% of all machine translations on the platform. This makes it the third most-used machine translation engine across all published translations just four months after launch. 2/5
-
GEM-2: Novel Method for Full-Range Many-Body Molecular Interactions
By
–
Combining data-driven & first-principles approaches to build a model, we proposed GEM-2, a novel method that comprehensively considers full-range many-body interactions in molecules.
Paper: https://
arxiv.org/abs/2208.05863
GitHub at #PaddlePaddle: https://
github.com/PaddlePaddle/P
addleHelix/tree/dev/apps/pretrained_compound/ChemRL/GEM-2
… -
Andrew builds new feature for decentralized Mastodon alternative
By
–
Andrew's building that feature for his little Mastodon alternative right here, and I'm watching with extreme interest https://
github.com/andrewgodwin/t
akahe/commit/dbe57075d386d7474bafc208b654507d9a2d769e
…