Edit model card

Conclusion

While significantly better at understanding and describing emotions and details in images compared to LLaVA-1.5-7b-hf, the fine-tuned model struggles with recognizing text.

Train Loss

loss

Test

A comparative analysis of emoji in prompts, differents between the original model and its fine-tuned counterpart.
Original Model:https://huggingface.co/llava-hf/llava-1.5-7b-hf/
meme01 meme02 meme03

Fine-tuned Lora Model:https://huggingface.co/REILX/llava-1.5-7b-hf-meme-lora
meme01 meme02 meme03

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • cutoff_len: 2048
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 8
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 5.0
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train REILX/llava-1.5-7b-hf-meme-lora

Collection including REILX/llava-1.5-7b-hf-meme-lora