Português
Abrir no Telegram

Post Build your own decision model

22 de outubro de 2026
P
PythonHub
Link
clique para mostrar
Build your own decision model Nish Tahir shows how to turn a small Qwen model into a fixed-choice decision model by masking outputs to allowed tokens, then evaluates and fine-tunes it on CommonsenseQA. Because the raw token probabilities are overconfident, he applies temperature scaling so the reported confidence better matches actual accuracy. https://nishtahir.com/build-your-own-decision-model/
1 · 107 ·

Por perto no feed

PPythonHubBuilding a lift scheduling algorithm in Python The post demonstrates how to implement a multi-elevator scheduling algorithm in Python using the LOOK algorithm tPPythonHubPython 3.15 for Data Scientists: Lazy Imports, frozendict, and Tachyon Python 3.15 adds lazy imports, a built-in frozendict, and the Tachyon profiler. Learn how
esta mensagem
PPythonHubsecurity-suite Open-source security suite for OSINT, web scanning, API testing, SIEM integration, and AI-powered analysis. https://github.com/TheSecuredAnalyst/PPythonHubBuilding a GPU Compiler from Scratch Progressive multi-level IR lowering systematically transforms high-level PyTorch graphs into optimized CUDA code through si

Um feed público aberto do índice de busca ChatCrawler — “o Google do Telegram público”; atualizado à medida que a comunidade é rastreada. Horários em UTC.

Somente conteúdo público, API oficial do Telegram. Sobre · Perguntas frequentes · Limites do índice · Remover uma página · Catálogo · Busca · Como calculamos