Excited to feature Tamper-Resistant Safeguards for Open-Weight LLMs from @lapisrocks
! Introducing the first safeguards for LLMs that resist fine-tuning attacks, showing the power of tamper-resistance to make open-weight LLMs safer. @rishub_t is here to answer your questions!
OPEN SOURCE
-
Tamper-Resistant Safeguards for Open-Weight LLMs
By
–
-
MergeKit and PruneMe: Essential Tools for Model Optimization
By
–
No, I would recommend libraries like MergeKit or PruneMe (
https://
github.com/arcee-ai/Prune
Me
…) from @arcee_ai for pruning. -
Modular Speech-to-Speech Pipeline Achieves Sub-500ms Latency
By
–
this modular speech-to-speech pipeline repo with <500 ms second latency (on a local GPU) is going crazy
— Thomas Wolf (@Thom_Wolf) 16 août 2024
Impressive what a well tuned pipeline of stt-llm-tts can do
cool work by @eustachelb with @reach_vb and @andi_marafioti
find the code here: https://t.co/HrbqSWQ3sj pic.twitter.com/HDkEnVntKNthis modular speech-to-speech pipeline repo with <500 ms second latency (on a local GPU) is going crazy Impressive what a well tuned pipeline of stt-llm-tts can do cool work by @eustachelb with @reach_vb and @andi_marafioti find the code here: https://
github.com/eustlb/speech-
to-speech
… -
Open-Source OCR Development for Asian Languages
By
–
Who’s working on (open-source ai for) OCR for languages spoken in Asia? Thinking in particular Hindi, Nepali but also wider
-
FLUX Image Generation Model Creates Open-Source AI Storm
By
–
wow FLUX the image-generation model from @bfl_ml has taken the open-source ai world totally by storm never seen so many derivative/spaces/demos of a model trending at the same time
-
AI Boosts Walmart Productivity; New Models and Jobs Emerge
By
–
Top stories in AI today: -AI makes Walmart 100x more productive
-SoftBank’s AI chip faces setback
-Create a Siri-like voice assistant
-Hermes 3 is the newest open-source model
-5 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/ai-makes-wal
mart-more-productive
… -
Sarvam AI Launches Open-Source Indic Language Model Sarvam 2B
By
–
Sarvam AI, a Bengaluru-based startup, has introduced an open-source foundational model supporting 10 Indian languages, including Hindi, Tamil, Bengali, and more. In addition, the company has released Sarvam 2B, a 2-billion-parameter Indic large language model trained on a
-
RAG Techniques Repository: Advanced Retrieval-Augmented Generation Methods
By
–
https://
github.com/NirDiamant/RAG
_Techniques
… -
Local LLM Support Coming to AI People Platform
By
–
A year ago there were no local LLMs that were smart enough to handle AI People. But today it looks much better. One of our first milestones after the alpha launch is to add a local LLM support. So, yes, I hope local LLM is possible.