mradermacher
/

Faro-Yi-34B-200K-i1-GGUF

Inference Endpoints

Model card Files Files and versions Community

mradermacher commited on 2 days ago

Commit

60c13ef

•

1 Parent(s): 7425e78

auto-patch README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ---
-base_model: wenbopan/Faro-Yi-34B-200K
 datasets:
 - wenbopan/Fusang-v1
 - wenbopan/OpenOrca-zh-20k
@@ -14,7 +14,7 @@ quantized_by: mradermacher
 <!-- ### convert_type:  -->
 <!-- ### vocab_type:  -->
-weighted/imatrix quants of https://huggingface.co/wenbopan/Faro-Yi-34B-200K
 **This uses my "quarter" training set of 40k tokens as the model overflowed after 25k tokens with the standard set.**

 ---
+base_model: wenbopan/Faro-Yi-34B
 datasets:
 - wenbopan/Fusang-v1
 - wenbopan/OpenOrca-zh-20k
 <!-- ### convert_type:  -->
 <!-- ### vocab_type:  -->
+weighted/imatrix quants of https://huggingface.co/wenbopan/Faro-Yi-34B
 **This uses my "quarter" training set of 40k tokens as the model overflowed after 25k tokens with the standard set.**