Phi-3-mini-4k-instruct - bnb 4bit

Model creator: Microsoft
Original model: Phi-3-mini-4k-instruct

Description

This model is 4bit quantized version of Phi-3-mini-4k-instruct using bitsandbytes. It's designed for fine-tuning! The PAD token is set as "<|endoftext|>".

Downloads last month: 84

Safetensors

Model size

2.07B params

Tensor type

F32

BF16

Inference Examples

Text Generation

Inference API (serverless) has been turned off for this model.

Model tree for leliuga/Phi-3-mini-4k-instruct-bnb-4bit

Base model

microsoft/Phi-3-mini-4k-instruct

Quantized

(98)

this model

Space using leliuga/Phi-3-mini-4k-instruct-bnb-4bit 1

Collection including leliuga/Phi-3-mini-4k-instruct-bnb-4bit

bnb-4 bit

Collection

A 4-bit quantized version models designed for fine-tuning. Demo: https://colab.research.google.com/drive/19UpFUjtbJoLua-4DMb1JKKwJAcvMyMHb • 21 items • Updated Jun 28