Kürzlich aktualisierte Kanäle

Wählen, um nur diesen Kanal zu sehenAlle Kanäle →
Matthew Bermangestern +251Theo - t3․gggestern +20AI Engineergestern +6The Buildersgestern +1a16zgestern +2硅谷101gestern +1SemiAnalysisgestern +1Chris WilliamsongesternCheeky PintgesternInvest Like The Bestgestern

Ergebnisse

5 Artikel
Sortieren
ThemaQuantizationPersonMatthew Berman
3 Folien5:27EN
Matthew Berman· 29. Jan. 2025Ways to Try DeepSeek R1: Hosted and Local Distilled ModelsMatthew Berman · Forward FutureMatthew Berman demonstrates DeepSeek chat, Groq’s hosted distill and a local model in LM Studio.Local inferenceOpen-weight modelsQuantization
8 Folien13:19EN
Matthew Berman· 18. Jan. 2024Running a Local Language Model as an Offline BackupMatthew Berman · Forward FutureMatthew Berman demonstrates a 2024 local-model setup, from selecting a quantized model and storing it on an external drive to planning backup power.Local inferenceFoundation ModelsInfrastruktur & Deployment+1
3 Folien6:11EN
Matthew Berman· 31. Aug. 2023Running WizardCoder Locally with Text Generation WebUIMatthew Berman · Forward FutureMatthew Berman walks through a 2023 setup for a quantized Code Llama-based coding model, from the Python environment to a simple test prompt.Local inferenceCoding-AgentenOpen-weight models+1
4 Folien7:21EN
Matthew Berman· 26. Juni 2023Testing Orca Mini 13B, an Unofficial Model Inspired by OrcaMatthew Berman · Forward FutureMatthew Berman loads a quantized Orca Mini 13B and tries coding, reasoning, arithmetic, and summarization prompts. His 2023 informal test produces several failures and a few successes.Open-weight modelsEvalsDistillation+2
3 Folien8:51EN
Matthew Berman· 2. Juni 2023Falcon 40B: A 2023 Leaderboard Result and a Slow GPU TestMatthew Berman · Forward FutureMatthew Berman tries a quantized Falcon 40B Instruct checkpoint on a hosted GPU and finds useful output but slow generation.Open-weight modelsFoundation ModelsLocal inference+1