solidrust/dolphin-2.9-llama3-8b-AWQ

cognitivecomputations/dolphin-2.9-llama3-8b AWQ

Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations

Discord: https://discord.gg/8fbBeC7ZGx

My appreciation for the sponsors of Dolphin 2.9:

• Crusoe Cloud - provided excellent on-demand 10xL40S node

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.

It took 2.5 days on 8x L40S provided by Crusoe Cloud

This model was trained FFT on all parameters, using ChatML prompt template format.

example:

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant