microsoft__Phi-4-reasoning-plus_RTN_w4g128

This is a 4-bit RTN (Round-To-Nearest) quantized version of microsoft/Phi-4-reasoning-plus.

Quantization Details

• Method: RTN (Round-To-Nearest)
• Bits: 4-bit
• Group Size: 128
• Base Model: microsoft/Phi-4-reasoning-plus

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "quantpa/microsoft__Phi-4-reasoning-plus_RTN_w4g128"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

# Use the model for inference

Model Details

• Quantization: RTN 4-bit
• Original Model: microsoft/Phi-4-reasoning-plus
• Quantized by: quantpa