Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations
This model is based on Llama-3-8b, and is governed by
META LLAMA 3 COMMUNITY LICENSE AGREEMENT
The base model has 8k context, and the full-weight fine-tuning was with 4k sequence length.
This model was trained FFT on all parameters, using ChatML prompt template format.
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant