Check it out here: https://
github.com/microsoft/mark
itdown
…
@reach_vb
-
Microsoft Releases Markdown Processing Tool on GitHub
By
–
-
Microsoft Open Sources MarkItDown File to Markdown Converter
By
–
Microsoft open sourced MarkItDown – convert files to Markdown – perfect for using with LLMs!
-
Alibaba Qwen’s Significant Impact on Open Source AI Development
By
–
The impact @Alibaba_Qwen has had to open AI/ ML is understated! Literally paving way to SoTA! 🤯 https://t.co/VJlpZ5QvHd pic.twitter.com/kc9V6oG9Zd
— Vaibhav (VB) Srivastav (@reach_vb) 16 décembre 2024The impact @Alibaba_Qwen has had to open AI/ ML is understated! Literally paving way to SoTA!
-
Apollo-3B multimodal AI model now available for testing
By
–
Play with the model directly over here: https://
huggingface.co/spaces/Apollo-
LMMs/Apollo-3B
… -
Meta Apollo Multimodal Models: 7B SoTA Video Understanding
By
–
Let's gooo! @AIatMeta released Apollo Multimodal Models Apache 2.0 licensed – 7B SoTA & beats 30B+ checkpoints🔥
— Vaibhav (VB) Srivastav (@reach_vb) 16 décembre 2024
Key insights:
> 1.5B, 3B and 7B model checkpoints
> Can comprehend up-to 1 hour of video 🤯
> Temporal reasoning & complex video question-answering
> Multi-turn… pic.twitter.com/v8bjDCp6qdLet's gooo! @AIatMeta released Apollo Multimodal Models Apache 2.0 licensed – 7B SoTA & beats 30B+ checkpoints Key insights: > 1.5B, 3B and 7B model checkpoints
> Can comprehend up-to 1 hour of video > Temporal reasoning & complex video question-answering
> Multi-turn -
All Models BF16: Context Length Maximization via TGI v3
By
–
All models are bf16. re: context, I know in past we have had restricted usage during spikes, would need to double check for 3.3. We do try to maximise the context length where possible. btw all powered via TGI v3:
-
Inference API Authentication and Rate Limiting Protection
By
–
all calls to Inference API are authenticated and are rate limited above certain limits to avoid abuse – so no matter the tier you'd be rate-limited if many people use it.