PinnedThanks for the appreciation, Its surreal for me to get acknowledged from the author itself.Feb 1, 2024Feb 1, 2024
Papers Explained 290: rStar-MathrStar-Math demonstrates that small language models (SLMs) can rival or even surpass the math reasoning capability of OpenAI o1, without…2d ago2d ago
Papers Explained 289: V-STaRVerification for Self-Taught Reasoners (V-STaR) utilizes both the correct and incorrect solutions generated during the self-improvement…3d ago3d ago
Papers Explained 288: STaRSelf-Taught Reasoner (STaR) is a technique to iteratively leverage a small number of rationale examples and a large dataset without…4d ago4d ago
Papers Explained 287: NuExtractNuExtract is a lightweight text-to-JSON LLM, that allows extraction of arbitrarily complex information from text and turns it into…5d ago5d ago
Papers Explained 286: NuNERNuNER is a compact language representation model specialized in the Named Entity Recognition (NER) task. It can be fine-tuned to solve…6d ago6d ago
Papers Explained 285: OpenScholarOpenScholar is a specialized retrieval-augmented language model that answers scientific queries by identifying relevant passages from 45…Jan 10Jan 10
Papers Explained 284: OLMo 2OLMo 2 are dense autoregressive models with improved architecture and training recipe, pre-training data mixtures, and instruction tuning…Jan 9Jan 9
Papers Explained 283: Tulu V3TÜLU 3 is a family of fully-open state-of-the-art post-trained models. It includes data, code, and training recipes, serving as a…Jan 8Jan 8
Papers Explained 282: Tulu V2Since the release of TÜLU, open resources for instruction tuning have developed quickly, from better base models to new finetuning…Jan 7Jan 7
