Ollama v0.35.1 版本更新
v0.35.1
重點導讀
Ollama v0.35.1 版本更新,加入多模態決策模型 Clef 與 Clef Flash,並擴充搜尋與 Modelfiles 功能。
- 核心新增:加入 Cloudflare 開源決策模型 Clef (27B) 與 Clef Flash (9B),支援影像與文字同時輸入。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
推薦理由
本次更新加入了 Clef 與 Clef Flash 多模態決策模型,並提升網路搜尋上限,支援 Modelfiles 宣告功能,讓使用者可即時體驗更強大模型能力。
正文 · 原文
Clef decision models
Ollama now supports Clef and Clef Flash, Cloudflare's new open-source decision models, through /v1/systemone.
Clef (27B) and Clef Flash (9B) are multimodal: requests can now include images alongside the text state, shared by all questions and scored jointly with it.
curl http://localhost:11434/v1/systemone -d '{
"model": "clef-flash",
"state": "The user took this screenshot.",
"images": ["<base64-encoded image>"],
"questions": {
"has_ollama": {"type": "noul", "instructions": "Does this image contain Ollama?"}
}
}'
{
"model": "clef-flash",
"answers": {
"has_ollama": {
"type": "noul",
"noul": 0.958
}
},
"usage": {
"input_tokens": 548,
"output_tokens": 0
}
}
What's Changed
- Models using web search can now perform up to ten searches per response, up from three
- Modelfiles now support
CAPABILITYdeclarations, so model creators can explicitly declare what a model can do. Declarations are preserved when creating from GGUF or safetensors, through model inheritance, and on Modelfile export ollama showand the model list now report onlydecisionas the capability for decision models, so clients no longer offer them for general chat, tools, or thinking- Updated llama.cpp and the MLX engine
Full Changelog: v0.35.0...v0.35.1
來源: ollama release (github.com)
開啟原文