README.md

metadata

license: apache-2.0
language:
  - en
base_model:
  - Qwen/Qwen2.5-0.5B-Instruct
new_version: ShubhaLabs/quantized_qwen_model

Quantized Qwen Model

This repository contains a quantized version of the Qwen model for causal language modeling.

Model Details

• Model Type: Qwen2ForCausalLM
• Quantization: Dynamic Quantization

Usage

You can load this model using the Hugging Face Transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("ShubhaLabs/quantized_qwen_model")
tokenizer = AutoTokenizer.from_pretrained("ShubhaLabs/quantized_qwen_model")