LoneStriker commited on
Commit
b17120c
1 Parent(s): 2947882

Added note on repetition penalty setting

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -9,6 +9,8 @@ datasets:
9
  # Fine-tune of Y-34B with Spicyboros-3.1
10
  One epoch of fine tuning with @jondurbin's SpicyBoros-3.1 dataset. 4.65bpw should fit on a single 3090/4090, 5.0bpw, 6.0bpw, and 8.0bpw will require more than one GPU 24 GB VRAM GPU.
11
 
 
 
12
  # Original Yi-34B Model Card Below
13
  <div align="center">
14
 
@@ -54,4 +56,4 @@ Although we use data compliance checking algorithms during the training process
54
  ## License
55
 
56
  The Yi series model must be adhere to the [Model License Agreement](https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE).
57
- For any questions related to licensing and copyright, please contact us ([[email protected]](mailto:[email protected])).
 
9
  # Fine-tune of Y-34B with Spicyboros-3.1
10
  One epoch of fine tuning with @jondurbin's SpicyBoros-3.1 dataset. 4.65bpw should fit on a single 3090/4090, 5.0bpw, 6.0bpw, and 8.0bpw will require more than one GPU 24 GB VRAM GPU.
11
 
12
+ **Please note:** you may have to turn down repetition penalty to 1.0. The model seems to get into "thesaurus" mode sometimes without this change.
13
+
14
  # Original Yi-34B Model Card Below
15
  <div align="center">
16
 
 
56
  ## License
57
 
58
  The Yi series model must be adhere to the [Model License Agreement](https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE).
59
+ For any questions related to licensing and copyright, please contact us ([[email protected]](mailto:[email protected])).