This model is based on Mistral-7b-v0.2.
The base model has 32k context, and the full-weights fine-tune was with 16k sequence lengths.
Dolphin-2.8 has a variety of instruction, conversational, and coding skills.
Dolphin is uncensored. The dataset was filtered by the creators to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. You are responsible for any content you create using this model.
Dolphin is licensed Apache 2.0. The creators grant permission for any use including commercial. Dolphin was trained on data generated from GPT4 among other models.
Have the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo QuantFactory/dolphin-2.8-mistral-7b-v02-GGUF ./model-folderdphn/dolphin-2.8-mistral-7b-v02