phi4 - Ollama 框架

phi4:最新

7.4M 下载更新 1 年前

Phi-4 是微软出品的 140 亿参数、最先进的开源模型。

14b

ollama run phi4

curl https://:11434/api/chat \
  -d '{
    "model": "phi4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='phi4',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'phi4',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

详情

1年前更新

1年前

ac896e5b8b34 · 9.1GB ·

模型

架构phi3

·

参数14.7B

·

量化Q4_K_M

9.1GB

许可

Microsoft. Copyright (c) Microsoft Corporation. MIT License Permission is hereby granted, free of ch

1.1kB

参数

{ "stop": [ "<|im_start|>", "<|im_end|>", "<|im_sep|>" ] }

82B

模板

{{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 -}} <|im_start|>{{ .R

275B

自述文件

Phi-4 是一个 14B 参数的、最先进的开源模型，构建于合成数据集、过滤后的公共领域网站数据以及获取的学术书籍和问答数据集的混合之上。

该模型经过了严格的增强和对齐过程，结合了监督微调和直接偏好优化，以确保精确的指令遵循和强大的安全措施。

上下文长度： 16k 个 token

主要用例

该模型旨在加速对语言模型的研究，作为构建基于生成式 AI 功能的基础。它为需要以下功能的通用 AI 系统和应用程序提供用途：

内存/计算受限的环境。
延迟受限的场景。
推理和逻辑。

超出范围的使用案例

这些模型并非专门为所有下游目的而设计或评估，因此

开发者应在选择使用案例时考虑语言模型的常见局限性，并在特定下游使用案例中使用之前评估和缓解准确性、安全性和公平性，尤其是在高风险场景中。
开发者应了解并遵守适用的法律或法规（包括隐私、贸易合规法律等），这些法律或法规与其使用案例相关，包括该模型对英语的关注。
本自述文件中的任何内容均不应解释为或被视为对模型发布许可的限制或修改。

<img src="https://ollama.ac.cn/assets/library/phi3.5/dbf19a17-e3fd-46b6-a059-e6b4f1fae59f" width="320" />

**Phi-4** is a 14B parameter, state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets.

![Phi-4 benchmark](/assets/library/phi4/67391ae2-e565-4173-ac3c-5e49bc977ac4)

The model underwent a rigorous enhancement and alignment process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures.

**Context length:** 16k tokens

![Phi-4 performance eval by Microsoft](/assets/library/phi4/5da7d0b6-53df-42f9-9c1b-651bfc380cdd)

### Primary use cases

The model is designed to accelerate research on language models, for use as a building block for generative AI powered features. It provides uses for general purpose AI systems and applications (primarily in English) which require:

1. Memory/compute constrained environments.
2. Latency bound scenarios.
3. Reasoning and logic.

### Out-of-scope use cases

The models are not specifically designed or evaluated for all downstream purposes, thus:

1. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fairness before using within a specific downstream use case, particularly for high-risk scenarios.
2. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case, including the model’s focus on English.
3. Nothing contained in this readme should be interpreted as or deemed a restriction or modification to the license the model is released under.

粘贴、拖放或单击以上传图像（.png、.jpeg、.jpg、.svg、.gif）