Thera-Bot-2025-04-28_04.56.49

This model is a fine-tuned version of Navid-AI/Yehia-7B-preview on an unknown dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 2

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.4.1+cu121
• Datasets 3.5.1
• Tokenizers 0.21.1

Other info

• Credits to this research paper: Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory
• Original dataset: cactus-camel/cactus
• Preprocessed dataset 🛠️🧹: Mariam23232/cactus-instruction-template
• Model selected to fine tune 🤖: Navid-AI/Yehia-7B-preview
  • why❓
    • From top arabic open source LLMs
    • 7 Billion parameter
    • English language support in addition to arabic
• Evaluation dataset: cactus-camel/CounselingEval
• GGUF Format of the model: Thera-Bot-2025-04-28_04.56.49-GGUF
  • File name to be used: Therabot-1stEpochEnd-Q4_K_M.gguf