Can't wait to see what the young #devs build!
CODE
-
PaliGemma Android Implementation with Hugging Face Gradio API
By
–
PaliGemma Android HF
— AK (@_akhaliq) 23 septembre 2024
github: https://t.co/A0oBkmj39S
This repository is an implementation of inferring the PaliGemma Vision Language Model on Android using Hugging Face-Gradio Client API for tasks such as zero-shot object detection, image captioning and visual… pic.twitter.com/rfB2kR8ijhPaliGemma Android HF github: https://
github.com/NSTiwari/PaliG
emma-Android-HF
… This repository is an implementation of inferring the PaliGemma Vision Language Model on Android using Hugging Face-Gradio Client API for tasks such as zero-shot object detection, image captioning and visual -
GraphRAG: Improving RAG Accuracy Through Entity Relationships
By
–
This survey paper (link provided in alt/image description) is a great read on GraphRAG, improving standard RAG systems' accuracy. Graph RAG uses relationships between enttiies to improve information retrieval, leading to more accurate and context-aware responses!
-
Open Source LLM Tool Reaches 30K GitHub Stars Milestone
By
–
30K GitHub Stars !!! Just over a year ago, we embarked on this journey, and today we’re thrilled to celebrate 30K stars and 15K forks on GitHub! We’re committed to continuously improving and becoming the best tool for building LLM apps Thank you, open source community
-
PDF2Audio Demo – Convert Documents to Speech
By
–
demo: https://
huggingface.co/spaces/lamm-mi
t/PDF2Audio
… -
Tokenization of ‘r’ same in both cases, questioning expectation
By
–
Why would you expect that to matter? “ r” is tokenized the same way in both cases. Either way, no:
-
OpenMusic: Diffusion Model That Generates Music
By
–
🎶 OpenMusic
— AK (@_akhaliq) 23 septembre 2024
Diffusion That Plays Music 🎧 🎹
github: https://t.co/l3QK4VLqvh
demo: https://t.co/ZnDaiI20Ow
model: https://t.co/DvTxqc49CU pic.twitter.com/s6C9LRy0L6OpenMusic Diffusion That Plays Music github: https://
github.com/ivcylc/qa-mdt
demo: https://
huggingface.co/spaces/jadecho
ghari/OpenMusic
…
model: https://
huggingface.co/jadechoghari/o
penmusic
… -
Claude 3.5 Sonnet Thinking Tokens and MMLU Score Implications
By
–
Sonnet has thinking tokens, yes. We don't know if they used them to get the MMLU score here https://
anthropic.com/news/claude-3-
5-sonnet
… But if more and more API models do this, I'll have to add them at some point -
MuCodec: Ultra Low-Bitrate Music Compression Codec
By
–
MuCodec Ultra Low-Bitrate Music Codec discuss: https://
huggingface.co/papers/2409.13
216
… Music codecs are a vital aspect of audio codec research, and ultra low-bitrate compression holds significant importance for music transmission and generation. Due to the complexity of music backgrounds and -
o1 tuned for high‑stakes reasoning beyond GPT‑4
By
–
3/ Another critical difference is o1’s ability to reason through complex tasks. GPT-4 made strides in general comprehension, but o1 is explicitly tuned for high-stakes problem-solving, whether it’s in mathematics, coding, or scientific research.