TGTGInsighttelegram intelligenceLIVE / telegram public index
← GitHub Trends
Back to channels

TGINSIGHT SIMILAR POSTS

Find similar content

Source channel @githubtrending · Post #14958 · Jul 14

View postView original

#python#agent#agentic_ai#grpo#kimi_ai#llms#lora#qwen#qwen3#reinforcement_learning#rl ART is a tool that helps you train smart agents for real-world tasks using reinforcement learning, especially with the GRPO method. The standout feature is RULER, which lets you skip the hard work of designing reward functions by using a large language model to automatically score how well your agent is doing—just describe your task, and RULER takes care of the rest. This makes building and improving agents much faster and easier, works for any task, and often performs as well as or better than hand-crafted rewards. You can install ART with a simple command and start training agents right away, even on your own computer or with cloud resources. https://github.com/OpenPipe/ART

Hashtags

#python#agent#agentic_ai#grpo#kimi_ai#llms#lora#qwen#qwen3#reinforcement_learning#rl
Results

2 similar posts found

Search: #jan

当前筛选 #jan清除筛选
Machinelearning

@ai_machinelearning_big_data · Post #8255 · 08/12/2025, 02:32 PM

Find similarView

🚀Jan-v1: локальная 4B-модель для веба — опенсорсная альтернатива Perplexity Pro 📌Что умеет - SimpleQA: 91% точности, чуть выше Perplexity Pro — и всё это полностью локально. - Сценарии: быстрый веб-поиск и глубокое исследование (Deep Research). Из чего сделана - Базируется на Qwen3-4B-Thinking (контекст до 256k), дообучена в Jan на рассуждение и работу с инструментами. Где запускать - Jan, llama.cpp или vLLM. Как включить поиск в Jan - Settings → Experimental Features → On - Settings → MCP Servers → включите поисковый MCP (например, Serper) Модели - Jan-v1-4B: https://huggingface.co/janhq/Jan-v1-4B - Jan-v1-4B-GGUF: https://huggingface.co/janhq/Jan-v1-4B-GGUF @ai_machinelearning_big_data #ai#ml#local#Qwen#Jan

Hashtags

#ai#ml#local#qwen#jan