Edit model card

Model Card for Mistral-7B-Evol-Ultrachat

Model Details

Model Description

Conversational model based on Mistral-7B. Trained using QLoRA + SFT on a RTX 3060. Uses the Mistral prompt format:

[INST] Using this information : {context} answer the Question : {query} [/INST]

  • Developed by: dylan9n
  • Model type: Conversational, Text Generation
  • Finetuned from model [optional]: Mistral-7B
Downloads last month
1
Safetensors
Model size
7.24B params
Tensor type
FP16
·

Dataset used to train dylan9n/Mistral-7B-Evol-Ultrachat