Yi models TECH REPORT just went live! Sharing our humble explorations launching, improving, innovating our base, chat, and vision-language models. Kudos to @01AI_Yi team behind the scenes. Love to hear the feedback from the community!
LLMS
-
Teaching LLMs to Reason with Reinforcement Learning
By
–
Teaching Large Language Models to Reason with Reinforcement Learning Havrilla et al.: https://
arxiv.org/abs/2403.04642 #ArtificialIntelligence #DeepLearning #MachineLearning -
Claude-3 Opus AI Ghostwriter Enabled in Reactor
By
–
We enabled Claude-3 Opus for all critical writing flows in Reactor . is today. OMG this AI ghostwriter is getting good. To the 1150 people in the beta group, enjoy! The posts it writes are pretty incredible.
-
Exploration-Based Trajectory Optimization for LLM Agents
By
–
Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents Song et al.: https://
arxiv.org/abs/2403.02502 #Artificialintelligence #DeepLearning #MachineLearning -
MediSwift-XL Sparse Model Outperforms Dense Competitor
By
–
(4/n) At 75% sparsity, MediSwift-XL outperforms the dense MediSwift-Med, despite having the same non-embedding parameters. This highlights the advantages of training larger but sparse models over smaller, densely parameterized models.
-
Dense Fine-Tuning Boosts MediSwift Biomedical Task Performance
By
–
(3/n) Dense fine-tuning and soft prompting enhance the performance of sparsely pre-trained MediSwift models on biomedical tasks (e.g., PubMedQA). This ensures high accuracy, thereby improving the efficiency-accuracy Pareto frontier. Pubmed QA leaderboard: https://
pubmedqa.github.io -
MediSwift: Sparse Biomedical Language Models Reduce Computational Costs
By
–
(1/n) Introducing MediSwift, the first suite of biomedical language models that employ sparse pre-training techniques to significantly reduce computational costs, while outperforming existing models up to 7B parameters on benchmark tasks such as PubMedQA. Paper:
-
LLMs Outperform Human Experts in Neuroscience Prediction
By
–
Large language models surpass human experts in predicting neuroscience results Luo et al.: https://
arxiv.org/abs/2403.03230 #ArtificialIntelligence #DeepLearning #MachineLearning -
Groq Processors Power OpenRouter Nitro Models With Impressive Speed
By
–
🚀 Thrilled to see our processors powering the latest Nitro models at @OpenRouterAI! The new speed benchmarks are impressive. It's exciting to be at the forefront of AI innovation with such high caliber developers. https://t.co/Gtfhy5fB1q
— Groq Inc (@GroqInc) 8 mars 2024Thrilled to see our processors powering the latest Nitro models at @openrouter
! The new speed benchmarks are impressive. It's exciting to be at the forefront of AI innovation with such high caliber developers. -
Groq’s Brighter Outlook Compared to Stranger in a Strange Land
By
–
"The man who introduces grok to Earth comes to an unpleasant end in Stranger in a Strange Land. For Groq, the outlook seems brighter." — @iainwmorris