This is first pass training. Further training and model update coming.

TinyLlama-Cinder-Agent-Rag

Special Thanks to https://nationtech.io/ for their generous sponorship in training this model.

This model is a fine-tuned version of Josephgflowers/TinyLlama-3T-Cinder-v1.2 on https://huggingface.co/datasets/Josephgflowers/agent_1.

Model description

This models is trained for RAG, Summary, Function Calling and Tool usage. Trained off of Cinder. Cinder is a chatbot designed for chat about STEM topics and storytelling. More information coming.

More model versions coming soon.

See https://huggingface.co/Josephgflowers/TinyLlama-Cinder-Agent-Rag/blob/main/tinyllama_agent_cinder_txtai-rag.py For usage example with wiki rag.

Intended uses & limitations

RAG, Chat, Summary, and tool usage.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 12
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.2.2+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1