Upload folder using huggingface_hub

README.md

@@ -4,19 +4,19 @@ tags:
 - merge
 - mergekit
 - lazymergekit
-- MediaTek-Research/Breeze-7B-32k-Base-v1_0
+- deepseek-ai/deepseek-llm-7b-base
 ---
 
 # Breeze-13B-32k-Base-v1_0
 
 Breeze-13B-32k-Base-v1_0 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
-* [MediaTek-Research/Breeze-7B-32k-Base-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-32k-Base-v1_0)
-* [MediaTek-Research/Breeze-7B-32k-Base-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-32k-Base-v1_0)
-* [MediaTek-Research/Breeze-7B-32k-Base-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-32k-Base-v1_0)
-* [MediaTek-Research/Breeze-7B-32k-Base-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-32k-Base-v1_0)
-* [MediaTek-Research/Breeze-7B-32k-Base-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-32k-Base-v1_0)
-* [MediaTek-Research/Breeze-7B-32k-Base-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-32k-Base-v1_0)
-* [MediaTek-Research/Breeze-7B-32k-Base-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-32k-Base-v1_0)
+* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
+* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
+* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
+* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
+* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
+* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
+* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
 
 ## 🧩 Configuration
 
@@ -26,53 +26,53 @@ merge_method: linear
 slices:
 - sources:
   - layer_range: [0, 8]
-    model: MediaTek-Research/Breeze-7B-32k-Base-v1_0    
+    model: deepseek-ai/deepseek-llm-7b-base
   - layer_range: [0, 8]
-    model: meta-llama/Meta-Llama-3-8B   
+    model: meta-llama/Meta-Llama-3-8B
     parameters:
       weight: 0
 - sources:
   - layer_range: [4, 12]
-    model: MediaTek-Research/Breeze-7B-32k-Base-v1_0    
+    model: deepseek-ai/deepseek-llm-7b-base
   - layer_range: [4, 12]
-    model: meta-llama/Meta-Llama-3-8B   
+    model: meta-llama/Meta-Llama-3-8B
     parameters:
       weight: 0
 - sources:
   - layer_range: [8, 16]
-    model: MediaTek-Research/Breeze-7B-32k-Base-v1_0    
+    model: deepseek-ai/deepseek-llm-7b-base
   - layer_range: [8, 16]
-    model: meta-llama/Meta-Llama-3-8B   
+    model: meta-llama/Meta-Llama-3-8B
     parameters:
       weight: 0
 - sources:
   - layer_range: [12, 20]
-    model: MediaTek-Research/Breeze-7B-32k-Base-v1_0    
+    model: deepseek-ai/deepseek-llm-7b-base
   - layer_range: [12, 20]
-    model: meta-llama/Meta-Llama-3-8B   
+    model: meta-llama/Meta-Llama-3-8B
     parameters:
       weight: 0
 - sources:
   - layer_range: [16, 24]
-    model: MediaTek-Research/Breeze-7B-32k-Base-v1_0    
+    model: deepseek-ai/deepseek-llm-7b-base
   - layer_range: [16, 24]
-    model: meta-llama/Meta-Llama-3-8B   
+    model: meta-llama/Meta-Llama-3-8B
     parameters:
       weight: 0
 - sources:
   - layer_range: [20, 28]
-    model: MediaTek-Research/Breeze-7B-32k-Base-v1_0    
+    model: deepseek-ai/deepseek-llm-7b-base
   - layer_range: [20, 28]
-    model: meta-llama/Meta-Llama-3-8B 
+    model: meta-llama/Meta-Llama-3-8B
     parameters:
       weight: 0
 - sources:
   - layer_range: [24, 32]
-    model: MediaTek-Research/Breeze-7B-32k-Base-v1_0    
+    model: deepseek-ai/deepseek-llm-7b-base
   - layer_range: [24, 32]
-    model: meta-llama/Meta-Llama-3-8B   
+    model: meta-llama/Meta-Llama-3-8B
     parameters:
       weight: 0
-tokenizer_source: union   
+tokenizer_source: union
 
 ```