大语言模型
对话
accounts/fireworks/models/phi-3-vision-128k-instruct 32K 1 服务商
Phi 3.5 Vision Instruct
accounts/fireworks/models/phi-3-vision-128k-instruct
Phi-3-Vision-128K-Instruct is a lightweight, state-of-the-art open multimodal model built from synthetic data and curated public web datasets, focusing on high-quality, reasoning-intensive text and vision data. It belongs to the Phi-3 family, with a multimodal version supporting a 128K context length (in tokens). The model undergoes rigorous enhancement, including supervised fine-tuning and direct preference optimization, to ensure accurate instruction following and strong safety measures.
模型简介
直接来自数据库的数据,保留结构化展示。
Phi-3-Vision-128K-Instruct is a lightweight, state-of-the-art open multimodal model built from synthetic data and curated public web datasets, focusing on high-quality, reasoning-intensive text and vision data. It belongs to the Phi-3 family, with a multimodal version supporting a 128K context length (in tokens). The model undergoes rigorous enhancement, including supervised fine-tuning and direct preference optimization, to ensure accurate instruction following and strong safety measures.
模型信息
模型属性、统计数据与发布时间。
模型 ID
accounts/fireworks/models/phi-3-vision-128k-instruct
模型类型
对话
上下文长度
32K
服务商数量
1
发布日期
热度状态
普通模型
浏览次数
2
点击次数
0
能力标签
模型支持的能力与特征。
视觉
提供方列表
数据库中的服务商信息。
暂无提供方信息
相关模型
按同类型和热度推荐