Update app.py

app.py

@@ -119,9 +119,9 @@ def repo_exists(repo_id: str) -> bool:
 def get_name(models: list[pd.Series], username: str, version=0) -> str:
     model_name = models[0]["Model"].split("/")[-1].split("-")[0].capitalize() \
                  + models[1]["Model"].split("/")[-1].split("-")[0].capitalize() \
-                 + "-7B"
+                 + "-8B"
     if version > 0:
-        model_name = model_name.split("-")[0] + f"-v{version}-7B"
+        model_name = model_name.split("-")[0] + f"-v{version}-8B"
 
     if repo_exists(f"{username}/{model_name}"):
         get_name(models, username, version+1)
@@ -144,74 +144,50 @@ def get_license(models: list[pd.Series]) -> str:
 
 
 def create_config(models: list[pd.Series]) -> str:
-    slerp_config = """
+    slerp_config = f"""
+slices:
+  - sources:
+      - model: {models[0]["Model"]}
+        layer_range: [0, 32]
+      - model: {models[1]["Model"]}
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: {models[0]["Model"]}
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+random_seed: 0
+    """
+    dare_config = f"""
 models:
-  - model: NousResearch/Meta-Llama-3-8B
-    # No parameters necessary for base model
-  - model: NousResearch/Meta-Llama-3-8B-Instruct
-    parameters:
-      density: 0.6
-      weight: 0.5
-  - model: mlabonne/OrpoLlama-3-8B
-    parameters:
-      density: 0.55
-      weight: 0.05
+- model: {models[0]["Model"]}
+  # No parameters necessary for base model
+- model: {models[1]["Model"]}
+  parameters:
+    density: 0.53
+    weight: 0.6
 merge_method: dare_ties
-base_model: NousResearch/Meta-Llama-3-8B
+base_model: {models[0]["Model"]}
 parameters:
-  int8_mask: true
-dtype: float16
+int8_mask: true
+dtype: bfloat16
+random_seed: 0
+""" 
+    stock_config = f"""
+models:
+  - model: mistralai/Mistral-7B-v0.1
+  - model: {models[0]["Model"]}
+  - model: {models[1]["Model"]}
+merge_method: model_stock
+base_model: mistralai/Mistral-7B-v0.1
+dtype: bfloat16    
 """
-    dare_config = slerp_config
-    stock_config = slerp_config
-#     slerp_config = f"""
-# slices:
-#   - sources:
-#       - model: {models[0]["Model"]}
-#         layer_range: [0, 32]
-#       - model: {models[1]["Model"]}
-#         layer_range: [0, 32]
-# merge_method: slerp
-# base_model: {models[0]["Model"]}
-# parameters:
-#   t:
-#     - filter: self_attn
-#       value: [0, 0.5, 0.3, 0.7, 1]
-#     - filter: mlp
-#       value: [1, 0.5, 0.7, 0.3, 0]
-#     - value: 0.5
-# dtype: bfloat16
-# random_seed: 0
-#     """
-#     dare_config = f"""
-# models:
-# - model: mlabonne/Meta-Llama-3-8B
-#   # No parameters necessary for base model
-# - model: {models[0]["Model"]}
-#   parameters:
-#     density: 0.53
-#     weight: 0.5
-# - model: {models[1]["Model"]}
-#   parameters:
-#     density: 0.53
-#     weight: 0.5
-# merge_method: dare_ties
-# base_model: mlabonne/Meta-Llama-3-8B
-# parameters:
-# int8_mask: true
-# dtype: bfloat16
-# random_seed: 0
-# """ 
-#     stock_config = f"""
-# models:
-#   - model: mlabonne/Meta-Llama-3-8B
-#   - model: {models[0]["Model"]}
-#   - model: {models[1]["Model"]}
-# merge_method: model_stock
-# base_model: mlabonne/Meta-Llama-3-8B
-# dtype: bfloat16    
-# """
-    yaml_config = random.choices([slerp_config, dare_config, stock_config], weights=[0.5, 0.4, 0.1], k=1)[0]
+    yaml_config = random.choices([slerp_config, dare_config, stock_config], weights=[0.3, 0.6, 0.1], k=1)[0]
 
     with open('config.yaml', 'w', encoding="utf-8") as f:
         f.write(yaml_config)