←搜索结果

搜索“NVIDIA”

按匹配度 · 共 264 条结果 清除搜索

星期二

  1. Ollama Blog

    Ollama 上线 OpenAI gpt-oss 20B 与 120B 开源权重模型

    Ollama 与 OpenAI 合作，将 gpt-oss 的 20B 和 120B 两个开源权重模型带到 Ollama，面向推理、智能体任务和开发者场景。模型支持函数调用、网页浏览、python 工具调用与结构化输出，可查看完整思维链，并可按低、中、高三档调节推理强度，采用 Apache 2.0 许可。OpenAI 将 MoE 权重以 MXFP4 格式量化到每参数 4.25 bits，使小模型可在 16GB 内存设备运行，大模型可放入单张 80GB GPU，Ollama 原生支持该格式并开发了新 kernel。

    welcome OpenAI gpt-oss

    odel is designed for lower latency, local, or specialized use-cases. 120B parameter model gpt-oss-120b model is designed for production, general purpose, high reasoning use-cases. NVIDIA and Ollama collaborate to accelerate gpt-oss on GeForce RTX and RTX PRO GPUs NVIDIA and Ollama are advancing their partnership to boost model performance on NVIDIA GeForce RTX and RTX PRO GPUs. This collaboration enables users on RTX-powered PCs to accurately leverage the capabilities of OpenAI’s gpt-oss model.

    匹配字段正文

    #company#模型发布#OpenAI#推理

星期三

  1. Mistral AI精选

    Mistral AI 发布 Codestral 25.08 及完整企业编程技术栈

    Mistral AI 发布 Codestral 25.08，并公布完整企业编程技术栈，称实测中已接受的补全增加 30%、建议后保留代码增加 10%，失控生成减少 50%。该技术栈整合 Codestral Embed、Devstral 与 Mistral Code，支持云、VPC 和本地部署，并提供 SSO、审计日志与使用可观测性；Mistral Code 的完整本地部署计划于 Q3 GA。

    Codestral Main

    s by wide margins Flexible architecture for any environment: Devstral is available in multiple sizes. The open-weight Devstral Small (24B, Apache-2.0) runs efficiently on a single Nvidia RTX 4090 or Mac with 32 GB RAM—ideal for self-hosted, air-gapped, or experimental workflows. The larger Devstral Medium is available through enterprise partnerships and our API for more advanced code understanding and planning capabilities. Open model for extensibility: Teams can fine-tune Devstral Small on prop

    匹配字段正文

    #lab#模型发布#编码#Agent

星期六

  1. Sarvam AI Blog

    Sarvam AI 发布 Sarvam-Translate，支持 22 种印度语言

    Sarvam AI 与 AI4Bharat 合作发布开源权重翻译模型 Sarvam-Translate，基于 Gemma3-4B-IT 微调，支持 22 种印度语言的段落级翻译，并为 15 种语言提供结构化内容翻译。模型可保留 HTML、LaTeX、化学公式、代码和 SRT 字幕等格式，仅翻译可读文本。语言专家人工评测显示其表现优于 Gemma3-27B-IT、Llama4 Scout 和 Llama-3.1-405B-FP8 等更大模型，模型已在 Hugging Face 开源并提供 API。

    Sarvam Translate

    g Post-Training Quantization (PTQ), leveraging a large and diverse calibration dataset to ensure robust 8-bit inference performance. The inference system is finely tuned to run on NVIDIA NIM with the TensorRT engine, utilising full FP8 kernels for improved throughput and efficiency. This optimised set up is available for use in our API store and can be tried in the dashboard. Known Limitations While this model supports 22 languages across a variety of tasks, performance can vary depending on the

    匹配字段正文

    #company#模型发布#开源生态#多模态

星期四

  1. Answer.AI 官方研发博客

    Answer.AI 与 LightOn 发布 ModernBERT，为 BERT 提供替代方案

    Answer.AI 与 LightOn 发布 ModernBERT，一个编码器专用模型系列，提供 base（149M 参数）和 large（395M 参数）两个版本，可作为 BERT 类模型的直接替换。它把上下文长度从多数编码器的 512 提升到 8192 token，并首次在编码器训练数据中加入大量代码，在检索、自然语言理解和代码检索任务上整体优于主流模型，速度最高可达 DeBERTa 的 4 倍。模型将随 transformers v4.48.0 发布，在此之前需从 main 分支安装，官方建议搭配 Flash Attention 2 使用。

    o 8,192 tokens, 16x longer than the mainstream models. Efficiency Here’s the memory (max batch size, BS) and Inference (in thousands of tokens per second) efficiency results on an NVIDIA RTX 4090 for ModernBERT and other decoder models: The first thing you might notice is that we’re analysing the efficiency on an affordable consumer GPU, rather than the latest unobtainable hyped hardware. First and foremost, ModernBERT is focused on practicality, not hype. As part of this focus, it also means we

    匹配字段正文

    #company#模型发布#开源生态#数据/训练