|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- Open-Orca/OpenOrca |
|
- jondurbin/airoboros-2.2.1 |
|
language: |
|
- en |
|
--- |
|
This Mistral 7B model is trained on a mix of datasets filtered for higher quality and output length. The mix of datasets was composed to increase reasoning and creativity. |
|
|
|
Datasets: |
|
|
|
The mix of datasets is composed of a filtered version of the OpenOrca and Airoboros 2.2.1 datasets. |
|
|
|
Training: |
|
|
|
Full model training took 17 hours with 4 epochs on 8x A100s. |
|
|
|
Prompt format: This model uses the ChatML prompt format (OpenAI's format). |
|
|
|
<|im_start|>system |
|
You are a helpful AI assistant.<|im_end|> |
|
<|im_start|>user |
|
{prompt}<|im_end|> |
|
<|im_start|>assistant |