sirmyrrh
/

Kyllima-34B-v1

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

sirmyrrh commited on Oct 3

Commit

0dcb6a1

•

1 Parent(s): a1a1682

Update README.md

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -19,7 +19,9 @@ This is a simple 50/50 merge of two of my favorite Yi 34B-based models for rolep
 200k context. Uncensored. Use with Alpaca-LimaRP or Vicuna prompt format.
 Recommended settings: lower temp, higher rep pen.
-The original upload had a broken tokenizer. If you downloaded before 9/29/24, please re-download. (Nope, it's still not right. Please don't download while I figure it out.)
 ### Merge Method
@@ -49,6 +51,7 @@ models:
     density: 0.5
     weight: 0.5
 parameters:
   int8_mask: true
   normalize: false
 tokenizer_source: base

 200k context. Uncensored. Use with Alpaca-LimaRP or Vicuna prompt format.
 Recommended settings: lower temp, higher rep pen.
+The original upload had a broken tokenizer. If you downloaded before 10/2/24, please re-download. (I think this is finally fixed for real.)
+GGUF available [here](https://huggingface.co/sirmyrrh/Kyllima-34B-v1).
 ### Merge Method
     density: 0.5
     weight: 0.5
 parameters:
+  embed_slerp: true
   int8_mask: true
   normalize: false
 tokenizer_source: base