Direct Preference Optimization vs. RLHF(together.ai)

29 points by summarity 1 year ago | 1 comments

DeepSearcher: A local open-source Deep Research(milvus.io)

185 points by stephen37 1 year ago | 23 comments

Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch(tongyi-agent.github.io)

340 points by meander_water 11 months ago | 136 comments

Blog post from Alibaba's Tongyi Lab introducing Tongyi DeepResearch, an open-source 30B MoE agent model, with benchmark results against OpenAI DeepResearch and others.

AdapTive-LeArning Speculator System (ATLAS): Faster LLM inference(together.ai)

192 points by alecco 1 year ago | 43 comments

Consistency diffusion language models: Up to 14x faster, no quality loss(together.ai)

203 points by zagwdt 8 months ago | 91 comments

RedPajama v2 Open Dataset with 30T Tokens for Training LLMs(together.ai)

213 points by programd 3 years ago | 51 comments