InferenceIllusionist commited on
Commit
f2a7ecb
1 Parent(s): 4f4c3d8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -22,7 +22,6 @@ An initial foray into the world of fine-tuning. The goal of this release was to
22
  * This is a quick experiment to determine the impact of DPO finetuning on the original base model
23
  * Ran for a little over an hour on a single A100
24
  * Internal benchmarks showed improvement over base model, awaiting final results
25
-
26
-
27
 
28
  *Requires [mistral-7b-mmproj-v1.5-Q4_1](https://huggingface.co/koboldcpp/mmproj/resolve/main/mistral-7b-mmproj-v1.5-Q4_1.gguf?download=true) file to be loaded in Kobold
 
22
  * This is a quick experiment to determine the impact of DPO finetuning on the original base model
23
  * Ran for a little over an hour on a single A100
24
  * Internal benchmarks showed improvement over base model, awaiting final results
25
+ * Precision: bfloat16
 
26
 
27
  *Requires [mistral-7b-mmproj-v1.5-Q4_1](https://huggingface.co/koboldcpp/mmproj/resolve/main/mistral-7b-mmproj-v1.5-Q4_1.gguf?download=true) file to be loaded in Kobold