phi3.5:latest

283.4K 9 months ago

A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.

3.8b

9 months ago

61819fb370a3 · 2.2GB

model
phi3
·
3.82B
·
Q4_0
template
{{ if .System }}<|system|> {{ .System }}<|end|> {{ end }}{{ if .Prompt }}<|user|> {{ .Prompt }}<|end
license
MIT License Copyright (c) Microsoft Corporation. Permission is hereby granted, free of charge, to
params
{ "stop": [ "<|system|>", "<|user|>", "<|end|>", "<|assistant|>"

Readme

Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites with a focus on very high-quality, reasoning dense data.

The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.

Long Context

Phi-3.5-mini supports 128K context length, therefore the model is capable of several long context tasks including long document/meeting summarization, long document QA, long document information retrieval.

References

Hugging Face