README.md

metadata

language: en
license: apache-2.0
tags:
  - qwen
  - fine-tuned
  - web-data
  - autonomous-training
datasets:
  - HuggingFaceM4_WebSight

qwen-web-HuggingFaceM4_WebSight-chunk-1-steps-160

This model is a fine-tuned version of Qwen2.5-0.5B on web data.

Training Details

• Dataset: HuggingFaceM4_WebSight
• Chunk: 1
• Global Steps: 160
• Focus: web_layout_understanding
• Training Date: 2025-07-30 13:59:23

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B")

# Load fine-tuned model
model = PeftModel.from_pretrained(base_model, "abdoosh1000/qwen-web-autonomous-models")

This model was trained using an autonomous training pipeline.