Nous Research released Arete-27B, an Apache 2.0 fine-tune of Qwen3.8-27B. On Nous’s 803-prompt eval, propaganda answers fell from 22% to 0.9% while Hermes Bench stayed flat at 65.60%.
The post Nous Research Releases Arete-27B that Cuts Qwen3.8-27B Propaganda From 22% to 0.9% appeared first on MarkTechPost.
Microsoft has released Microsoft-Decision-1, a decision model for routing, classification, verification and agent control. Microsoft-Decision-1 is a decision-scoring…
StepFun has released Step 5 Preview as open weights. FP8 and BF16 checkpoints are live on Hugging Face and ModelScope. Step 5 Preview is a sparse Mixture-of-Experts…
vLLM Semantic Router released d3-ultra, a 27B open-weight multimodal decision model. It reads text, images and video once, then returns probabilities for every answer…
Discussion (0)
No comments yet. Start the conversation!