Hugging Face's logo

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

Text Generation
Transformers
Safetensors
phi3
Phi-3-mini-4k-instruct
conversational
custom_code
text-generation-inference
4-bit precision
bitsandbytes
Model card Files Community
2
Phi-3-mini-4k-instruct-bnb-4bit / README.md
evaldas-leliuga's picture
evaldas-leliuga
Added model
c1345ed verified
preview code
|
raw
history blame contribute delete
762 Bytes
metadata
base_model: microsoft/Phi-3-mini-4k-instruct
license: other
license_name: mit
license_link: https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/raw/main/LICENSE
inference: false
model_creator: Microsoft
model_name: Phi-3-mini-4k-instruct
quantized_by: Leliuga
pipeline_tag: text-generation
tags:
  - Phi-3-mini-4k-instruct

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

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|>".