Edit model card

Training

axolotl was used for training on a 2x nvidia a40 gpu cluster.

the a40 GPU cluster has been graciously provided by Arc Compute.

trained on subset of koishi commit 6e675d1 for one epoch

  • asss
  • dolly
  • hh-rlhf
  • wizard evol

Base Model

rank 8 lora tune of mistralai/Mistral-7B-v0.1

Prompting

### System:

### Instruction:

### Response:
Downloads last month
3

Dataset used to train ewof/koishi-mini-vicuna-mistral-7b

Collection including ewof/koishi-mini-vicuna-mistral-7b