README.md

metadata

language: en
tags:
  - generated_from_trainer
  - fine-tuning
license: apache-2.0
datasets:
  - name_of_dataset
metrics:
  - accuracy
  - f1
model:
  - name: Qwen2VLForConditionalGeneration
    finetuned_from: Qwen/Qwen2-VL-2B-Instruct
    tasks:
      - text-generation

Fine-Tuned Qwen2vl Model

This repository contains a fine-tuned version of the Qwen2vl model for exploration purpose.

Model Files

• model.safetensors.index.json: The index for the model weights in safetensors format.
• model-00001-of-00003.safetensors: Part 1 of the model weights.
• model-00002-of-00003.safetensors: Part 2 of the model weights.
• model-00003-of-00003.safetensors: Part 3 of the model weights.
• config.json: Configuration file for the model architecture.
• tokenizer.json: Tokenizer file.
• tokenizer_config.json: Tokenizer configuration.
• special_tokens_map.json: Special tokens mapping.
• vocab.json: Vocabulary file.

Usage

To use this model, you can load it using the following code:

from transformers import AutoModel, AutoTokenizer, SafeTensorsLoader

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained("FatimaAziz/qwen2B_Finetunned4/")

# Load model with safetensors
model = SafeTensorsLoader.from_pretrained("FatimaAziz/qwen2B_Finetunned4/")

# If SafeTensorsLoader is not available, you might need to convert the model
# from safetensors to the standard format supported by AutoModel