Recently updated channels

Pick one to see only that channelBrowse all channels →
Matthew Bermantoday +270AI Engineertoday +6The Builderstoday +120VC with Harry Stebbingsyesterday +380Jane Streetyesterday +119Y Combinatoryesterday +1硅谷1012 days agoPragerU3 days agoa16z4 days ago +1SemiAnalysis4 days ago

Results

4 articles
Sort
TopicFine-tuningLengthUnder 15 min
5 slides12:03EN
Matthew Berman· Sep 6, 2024Reflection 70B: Self-Correction Claims and the Limits of a 2024 DemoMatthew Berman · Forward FutureMatthew Berman reviews a model trained to generate reflection steps. Its initial benchmark claims later proved difficult for independent evaluators to reproduce.AI HistoryFoundation ModelsEvals+2
2 slides6:28EN
Matthew Berman· Aug 29, 2023A Historical GPT-3.5 Fine-Tuning WalkthroughMatthew Berman · Forward FutureMatthew Berman demonstrates generating synthetic examples in Colab and training a model to use a distinctive tone.Fine-tuningSynthetic dataModels & training
2 slides8:49EN
Matthew Berman· Jul 19, 2023Llama 2’s 2023 Release: Model Sizes, License and SafetyMatthew Berman · Forward FutureMatthew Berman reviews Meta’s Llama 2 paper, its commercial license, model variants and safety evaluations.Open source & communityFoundation ModelsAI Alignment+1
4 slides11:42EN
Matthew Berman· May 31, 2023Guanaco and QLoRA: A 2023 Fine-Tuning and Model TestMatthew Berman · Forward FutureMatthew Berman reviews the QLoRA paper, explains the reported memory savings and tries Guanaco 65B on an informal prompt set.Fine-tuningQuantizationOpen-weight models+1