The format is ChatML. If you use this model let me know how it goes. It should be able to do a bit of everything but the main focus was not compromising on prose or coherence.

Training details:

1x RTX 4080 + x RTX 3090
Rank 64 RS-QLoRA
156 Hours runtime

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Dans-DiscountModels/Dans-Instruct-7b-v0.0.5

Base model

Dans-DiscountModels/mistral-7b-v0.3-ChatML

Finetuned

(5)

this model

Quantizations

2 models