Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original本文为自动采集的行业资讯。原文来源:hugg

AI News2026-09-190model

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers本文为自动采集的行业资讯。原文来源:huggingface.co

AI News2026-09-190model

Training a coding model to paint watercolours with TRL and OpenEnv

Training a coding model to paint watercolours with TRL and OpenEnv本文为自动采集的行业资讯。原文来源:huggingface.co

AI News2026-09-190model

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps本文为自动采集的行业资讯。原文来源:huggingface.co

AI News2026-09-191model

Perplexity trusts GPT-6 Astra with end-to-end systems

Perplexity uses Astra to write communications, change software, and monitor production systems, and checks in much less

AI News2026-09-190model

NASA 和 IBM 开源月球模型

NASA 和 IBM 开源了首个月球模型 NASA-IBM Lunar Foundation Model,模型权重与代码向全球研究者开放,以供下载、微调和试验。这是首批专门面向月球科学、可公开使用的智能分析工具之一,目标是把数十年来分散的月

AI News2026-09-194model
Submit Site