Upload folder using huggingface_hub

README.md

@@ -4,17 +4,17 @@ tags:
 - merge
 - mergekit
 - lazymergekit
+- rhysjones/phi-2-orange
 - cognitivecomputations/dolphin-2_6-phi-2
 - mrm8488/phi-2-coder
-- rhysjones/phi-2-orange
 ---
 
 # phi-2-ties
 
 phi-2-ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [rhysjones/phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange)
 * [cognitivecomputations/dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)
 * [mrm8488/phi-2-coder](https://huggingface.co/mrm8488/phi-2-coder)
-* [rhysjones/phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange)
 
 ## 🧩 Configuration
 
@@ -23,7 +23,7 @@ models:
   - model: rhysjones/phi-2-orange
     parameters:
       density: 0.5
-      weight: 0.4
+      weight: 0.3 
   - model: cognitivecomputations/dolphin-2_6-phi-2
     parameters:
       density: 0.5
@@ -43,7 +43,7 @@ dtype: float16
 ## 💻 Usage
 
 ```python
-!pip install -qU transformers accelerate einops
+!pip install -qU transformers accelerate
 
 from transformers import AutoTokenizer
 import transformers
@@ -59,7 +59,6 @@ pipeline = transformers.pipeline(
     model=model,
     torch_dtype=torch.float16,
     device_map="auto",
-    trust_remote_code=True
 )
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)

mergekit_config.yml

@@ -3,7 +3,7 @@ models:
   - model: rhysjones/phi-2-orange
     parameters:
       density: 0.5
-      weight: 0.4
+      weight: 0.3 
   - model: cognitivecomputations/dolphin-2_6-phi-2
     parameters:
       density: 0.5