Upload folder using huggingface_hub

README.md

@@ -4,14 +4,14 @@ tags:
 - merge
 - mergekit
 - lazymergekit
-- DiscoResearch/mixtral-7b-8expert
+- HuggingFaceH4/zephyr-7b-alpha
 - mlabonne/Marcoro14-7B-slerp
 ---
 
 # HerLlama-7B-slerp
 
 HerLlama-7B-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
-* [DiscoResearch/mixtral-7b-8expert](https://huggingface.co/DiscoResearch/mixtral-7b-8expert)
+* [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)
 * [mlabonne/Marcoro14-7B-slerp](https://huggingface.co/mlabonne/Marcoro14-7B-slerp)
 
 ## 🧩 Configuration
@@ -19,12 +19,12 @@ HerLlama-7B-slerp is a merge of the following models using [mergekit](https://gi
 ```yaml
 slices:
   - sources:
-      - model: DiscoResearch/mixtral-7b-8expert
+      - model: HuggingFaceH4/zephyr-7b-alpha
         layer_range: [0, 32]
       - model: mlabonne/Marcoro14-7B-slerp
         layer_range: [0, 32]
 merge_method: slerp
-base_model: DiscoResearch/mixtral-7b-8expert
+base_model: mlabonne/Marcoro14-7B-slerp
 parameters:
   t:
     - filter: self_attn