Papers, Models, Open Source : AI News

Timestamp00:00 Intro00:21 MoT03:07 JudgeLM05:52 Emulator for Fine-Tuned LLMs08:19 ConvNet matches ViT09:57 Zephyr Technical Paper12:08 Text to NeRF14:04 KITAB16:06 AlpaGasus17:43 Fine-Tuning Jailbreaks19:27 Vicuna Radiology21:04 QMoE32:38 Zephyr Model32:38 Marker 125:12 Narwhal Mistral Model Merges26:45 GradioLite28:14 RLMRec31:56 OpenAI Prepardness34:25 Poe Creator Monetization35:10 Draft Ai Executive Order

Links at the bottom section!!!

If you want to support the channelSupport here:Patreon – https://www.patreon.com/1littlecoder/Ko-Fi – https://ko-fi.com/1littlecoder

Follow me onTwitter – https://twitter.com/1littlecoderLinkedin – https://www.linkedin.com/in/amrrs/

Links

Papers

Mixture of Tokens: Efficient LLMs through Cross-Example Aggregation – https://arxiv.org/pdf/2310.15961.pdfJudgeLM – https://arxiv.org/pdf/2310.17631.pdfAn Emulator for Fine-Tuning Large Language Models using Small Language Modelshttps://arxiv.org/pdf/2310.12962.pdfConvNets Match Vision Transformers at Scale https://arxiv.org/pdf/2310.16764.pdfQMoE – https://arxiv.org/pdf/2310.16795.pdfZEPHYR: DIRECT DISTILLATION OF LM ALIGNMENT https://arxiv.org/pdf/2310.16944.pdfHYPERFIELDS: TOWARDS ZERO-SHOT GENERATION OF NERFS FROM TEXT https://arxiv.org/pdf/2310.17075.pdfKITAB – https://arxiv.org/pdf/2310.15511.pdfFine-tune LLMs for harmful response https://arxiv.org/abs/2310.03693 https://arxiv.org/pdf/2310.03693.pdfFeasibility of Using the Privacy-preserving Large Language Model Vicuna for Labeling Radiology Reports https://pubs.rsna.org/doi/epdf/10.1148/radiol.231147 

Models

Zephyr Beta https://huggingface.co/HuggingFaceH4/zephyr-7b-betaEric Hartford’s Dolphin2.1 with MetaMath-Mistral by Meta Math. Then that model was merged with and HuggingFace’s Zephyr-7b-beta https://huggingface.co/Vezora/Mistral-Narwhal-7b https://huggingface.co/Vezora/Mistral-Narwhal-7b-v2 

Open Source

Serverless Gradio (Gradio Lite) – https://www.gradio.app/guides/gradio-liteRLMRec: Representation Learning with Large Language Models for Recommendation https://github.com/hkuds/rlmrec#rlmrec-representation-learning-with-large-language-models-for-recommendationOpenAgents – https://github.com/xlang-ai/OpenAgents 

General NewsFrontier Risks and OpenAI preparedness Challenge https://openai.com/blog/frontier-risk-and-preparednessPoe Creator Monetization Program https://quorablog.quora.com/Introducing-creator-monetization-for-Poe

The post Papers, Models, Open Source : AI News appeared first on AIPressRoom.