ewof's picture
Update README.md
a828b70
|
raw
history blame
394 Bytes

axolotl was used for training on a 4x nvidia a40 gpu cluster.

the a40 GPU cluster has been graciously provided by Arc Compute. rank 8 lora merge

tune of mistral 7b

this is the format

### System:

### Instruction:

### Response:

trained on subset of koishi

  • asss
  • dolly
  • hh-rlhf
  • wizard evol