metadata

license: apache-2.0
datasets:
  - cognitivecomputations/dolphin
  - cognitivecomputations/dolphin-coder
  - ise-uiuc/Magicoder-OSS-Instruct-75K
  - teknium/openhermes
  - migtissera/Synthia-v1.3
language:
  - en

Model Description

This is fine-tuned model based on EmbeddedLLM/Mistral-7B-Merge-14-v0.3 for 3 epochs. The dataset used are:

dophin
dolphin-coder
Magicoder-OSS-Instruct-75K
openhermes
Synthia-v1.3

Chat Template

Prompt format: This model uses ChatML prompt format.

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

Training

The model has been fine-tuned for 3 epochs on 4 A100s using axolotl.

Shout-Out to OSS

Thank you to the Open Source AI community for bringing together marvelous code frameworks and datasets.