T
traeai
Sign in

模型

Gemma

别名:gemma3、gemma4

Google开发的系列大语言模型

已跟踪 20 条高相关材料

TraeAI 观察

相关材料

已收录 20 条与 Gemma 相关的内容,按评分排序。

How Trustpilot built a real-time architecture for data enrichment using Gemma

How Trustpilot built a real-time architecture for data enrichment using Gemma

Google Cloud Blog992 字 (约 4 分钟)
92

Trustpilot built a real-time data enrichment pipeline using fine-tuned Gemma models to process millions of reviews under strict latency and cost constraints, achieving near-teacher-model accuracy with full control.

入选理由:采用 google/gemma-2-9b 基础模型,通过共识标注生成高质量训练集,微调后准确率仅比教师模型低几个百分点。

FeaturedArticle#Gemma#Dataflow#LLM#Real-time Architecture#Fine-tuning英文
Google Developers Blog 图标

How the community trained Gemma to "Think" with Tunix and TPUs

Google Developers Blog1240 字 (约 5 分钟)
92

社区通过 Tunix 和 TPU 成功训练 Gemma 模型生成推理能力,提供可复现的训练方法。

入选理由:G-RaR 方法结合 SFT 和 GRPO,使用 Gemma-3-12B 作为评估模型,显著提升推理能力。

FeaturedArticle#Gemma#Tunix#TPU#LLM#推理训练中文
Towards Data Science 图标

How Much Does It Actually Cost to Run a Local LLM? (Euros per Million Tokens, Measured)

Towards Data Science2577 字 (约 11 分钟)
85

本地运行LLM成本可能低于云服务,Gemma26B模型每百万令牌仅需0.12欧元,但大模型能耗差异显著。

入选理由:Gemma26B模型本地运行成本0.12欧元/百万令牌,低于多数云API

FeaturedArticle#LLM#GPU#能耗计算#成本分析英文
Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding

Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding

Simon Willison's Weblog458 字 (约 2 分钟)
85

Ornith-1.0是DeepReinforce发布的开源大模型,基于Gemma和Qwen,支持多种参数规模,在编码任务中表现优异。

入选理由:Ornith-1.0提供9B到397B参数版本,兼容Apache 2.0许可证

FeaturedArticle#LLM#开源模型#编码基准#MIT许可证#DeepReinforce中英混合
Google OpenRL is an Experimental Self-hosted API for LLM Post-Training Fine-tuning

Google 推出 OpenRL,一个用于 LLM 微调的自托管 API,旨在简化强化学习流程并提升 GPU 利用率。

入选理由:OpenRL 允许在 Kubernetes 集群上运行多个 RL 任务,提升 GPU 利用率。

FeaturedArticle#Kubernetes#LLM#强化学习#AI#Google英文
Hugging Face Blog 图标

We got local models to triage the OpenClaw repo for FREE!*

Hugging Face Blog3088 字 (约 13 分钟)
85

Hugging Face 使用本地模型 Gemma 和 Qwen 实现 OpenClaw 仓库的自动化分类,无需依赖云端模型。

入选理由:使用本地模型 Gemma 和 Qwen 可实现 OpenClaw 仓库的实时分类任务。

FeaturedArticle#Hugging Face#本地模型#AI 代理#OpenClaw#分类任务英文
Using Scikit-LLM with Open-Source LLMs

Using Scikit‑LLM with Open‑Source LLMs

Machine Learning Mastery1080 字 (约 5 分钟)
85

This article shows how to use locally hosted open‑source LLMs (Llama 3, Mistral, Gemma) via Ollama together with Scikit‑LLM to perform zero‑shot text classification, all for free.

入选理由:通过 `ollama run <model>` 可在本地拉取并运行 Llama 3、Mistral 或 Gemma,端口默认 11434。

FeaturedArticle#Scikit‑LLM#Ollama#LLM#Zero‑shot#Python英文
Running Local AI on AMD

Running Local AI on AMD

Sam Witteveen3611 字 (约 15 分钟)
85

Sam Witteveen探讨了在AMD硬件上运行本地AI的可能性,强调了本地AI在隐私和成本控制方面的优势。

入选理由:本地AI模型如Qwen 3.6和Gemma在实际工作中表现出色。

FeaturedVideo#AMD#本地AI#硬件#隐私#成本控制英文
Make Gemma go brrrr!!! Multi-Token Prediction drafters are here for Gemma 4, making inference up to ...

Philipp Schmid宣布为Gemma 4模型推出多令牌预测(Multi-Token Prediction)drafters技术,实测推理速度提升最高达3倍,且输出质量零损失。

入选理由:Multi-Token Prediction drafters使Gemma 4推理速度最高提升3倍

FeaturedTweet#Gemma#LLM#inference#optimization#open-source中文
&gt; Ecosystem: Compatible with llama.cpp, MLX, @LMStudio, vLLM, @ollama, @UnslothAI, and SGLang.
&amp;g...

Google AI Developers: Gemma 4 Ecosystem Compatibility and Downloads

Google AI Developers(@googleaidevs)78 字 (约 1 分钟)
65

Google announces its model weights are compatible with major open-source ecosystems and can be directly downloaded from Hugging Face and Kaggle, lowering deployment barriers.

入选理由:Gemma 4 权重与 llama.cpp、vLLM、Ollama 等生态兼容,便于本地部署与推理。

FeaturedTweet#Gemma#Open-source Ecosystem#Model Deployment#Hugging Face#Kaggle英文
https://t.co/92AqGRscNo

Gemma-Skills Project Launch: Enhancing Gemma Model Agent Interaction Capabilities

Philipp Schmid(@_philschmid)44 字 (约 1 分钟)
65

The article introduces Google's Gemma-Skills skill library, designed to enhance Gemma model capabilities in agent interactions, supporting multimodal tasks and tool calling, but lacks detailed technical specifications or performance data.

入选理由:Google 发布了 Gemma-Skills 项目,用于增强 Gemma 模型的代理交互能力。

FeaturedTweet#Gemma#AI#GitHub#Model Skills#Agent Interaction英文
Host a sponsored Gemma hackathon for your local community. 🌐

Host a sponsored Gemma hackathon for your local community. 🌐

Google AI Developers(@googleaidevs)96 字 (约 1 分钟)
60

Google邀请开发者举办Gemma模型赞助的hackathon,旨在推动社区创新。

入选理由:Google赞助1-day hackathons on Kaggle,帮助开发者使用Gemma模型。

FeaturedTweet#Gemma#hackathon#Google#AI模型英文
Gemma support in @geminicli 🤗

`gemini gemma setup`
`gemini gemma start`

Gemma support in @geminicli 🤗 `gemini gemma setup` `gemini gemma start`

Patrick Loeber(@patloeber)244 字 (约 1 分钟)
60

Patrick Loeber宣布Gemma功能已集成到@geminicli中,用户可通过`gemini gemma setup`和`gemini gemma start`命令体验。此更新伴随Gemini CLI v0.40.0发布,重点改进包括分层内存、本地Gemma路由及简化UI。

入选理由:Gemma功能集成进Gemini CLI,简化模型路由操作。

FeaturedTweet#Gemma#Gemini CLI#Model Routing#CLI Tools#Product Update中文
Gemma 4 shifts Pareto Frontier on Code @arena.🔥

Among open models, Gemma-4-31b ranks #13 and Gemma...

Gemma 4 Shifts Pareto Frontier in Code Arena

Philipp Schmid(@_philschmid)193 字 (约 1 分钟)
55

The Gemma-4 series of open models ranks #13 (31b) and #17 (26b-a4b) in code performance, marking strong efficiency and local deployability on devices like MBP.

入选理由:Gemma-4-31b在开源代码模型中排名全球第13。

FeaturedTweet#Gemma#Code Model#Open Source AI中英混合
From Google I/O to building real world solutions in one weekend. Always inspired by the energy of th...

From Google I/O to building real world solutions in one weekend

Google AI Developers(@googleaidevs)109 字 (约 1 分钟)
45

Google AI Devs built real AI products within a weekend after Google I/O, but the post lacks technical depth or reusable methodology, focusing only on community energy.

入选理由:社区成员在Google I/O后48小时内基于Gemini+Gemma构建多模态代理和语音接口原型。

FeaturedTweet#Google I/O#Gemini#Gemma#AI Community英文
We made a skill for and using Gemma. 

```
npx skills add google-gemma/gemma-skills --skill gemma-de...

We made a skill for and using Gemma

Philipp Schmid(@_philschmid)64 字 (约 1 分钟)
40

This article introduces a skill named gemma-dev for using Google's Gemma model in development, installed via npx command, but lacks technical details.

入选理由:使用命令 `npx skills add google-gemma/gemma-skills --skill gemma-dev` 安装 Gemma 开发技能。

FeaturedTweet#Gemma#AI#Development Tool#X Platform英文

跨材料问答 · Gemma

回答基于:Gemma 相关 20 条材料
    0 / 500

    AI may generate inaccurate information. Please verify important content.