added Gemma2 models to default list

socialfoundations · Jun 30, 2024 · ccb3f19 · ccb3f19
1 parent 6703344
commit ccb3f19
Show file tree

Hide file tree

Showing 2 changed files with 32 additions and 29 deletions.
diff --git a/folktexts/cli/download_models.py b/folktexts/cli/download_models.py
@@ -12,38 +12,28 @@
 
 # Default list of models to download
 DEFAULT_MODEL_LIST = [
-    # OpenAI GPTs (all small models)
-    "openai-community/gpt2",
-    "openai-community/gpt2-large",
-    "openai-community/gpt2-xl",
-
-    # Google Gemma models
+    # Google Gemma2 models
     "google/gemma-2b",
     "google/gemma-1.1-2b-it",
-
     "google/gemma-7b",
     "google/gemma-1.1-7b-it",
 
     "google/gemma-2-9b",
     "google/gemma-2-9b-it",
-
     "google/gemma-2-27b",
     "google/gemma-2-27b-it",
 
     # Meta Llama3 models
     "meta-llama/Meta-Llama-3-8B",
     "meta-llama/Meta-Llama-3-8B-Instruct",
-
     "meta-llama/Meta-Llama-3-70B",
     "meta-llama/Meta-Llama-3-70B-Instruct",
 
     # Mistral AI models
     "mistralai/Mistral-7B-v0.1",
     "mistralai/Mistral-7B-Instruct-v0.2",
-
     "mistralai/Mixtral-8x7B-v0.1",
     "mistralai/Mixtral-8x7B-Instruct-v0.1",
-
     "mistralai/Mixtral-8x22B-v0.1",
     "mistralai/Mixtral-8x22B-Instruct-v0.1",
 
@@ -52,14 +42,12 @@
     "01-ai/Yi-34B-Chat",
 
     # Qwen2 models
-    "Qwen/Qwen2-1.5B",
-    "Qwen/Qwen2-1.5B-Instruct",
-
-    "Qwen/Qwen2-7B",
-    "Qwen/Qwen2-7B-Instruct",
-
-    "Qwen/Qwen2-72B",
-    "Qwen/Qwen2-72B-Instruct",
+    # "Qwen/Qwen2-1.5B",
+    # "Qwen/Qwen2-1.5B-Instruct",
+    # "Qwen/Qwen2-7B",
+    # "Qwen/Qwen2-7B-Instruct",
+    # "Qwen/Qwen2-72B",
+    # "Qwen/Qwen2-72B-Instruct",
 ]
 
 

diff --git a/folktexts/cli/launch_experiments_htcondor.py b/folktexts/cli/launch_experiments_htcondor.py
@@ -46,27 +46,42 @@
 
 # LLMs to evaluate
 LLM_MODELS = [
-    # ** Small models **
+    # Google Gemma2 models
     "google/gemma-2b",
     "google/gemma-1.1-2b-it",
-
-    # # ** Medium models **
     "google/gemma-7b",
     "google/gemma-1.1-7b-it",
-    "mistralai/Mistral-7B-v0.1",
-    "mistralai/Mistral-7B-Instruct-v0.2",
+
+    "google/gemma-2-9b",
+    "google/gemma-2-9b-it",
+    "google/gemma-2-27b",
+    "google/gemma-2-27b-it",
+
+    # Meta Llama3 models
     "meta-llama/Meta-Llama-3-8B",
     "meta-llama/Meta-Llama-3-8B-Instruct",
+    "meta-llama/Meta-Llama-3-70B",
+    "meta-llama/Meta-Llama-3-70B-Instruct",
 
-    # # ** Large models **
-    "01-ai/Yi-34B",
-    "01-ai/Yi-34B-Chat",
+    # Mistral AI models
+    "mistralai/Mistral-7B-v0.1",
+    "mistralai/Mistral-7B-Instruct-v0.2",
     "mistralai/Mixtral-8x7B-v0.1",
     "mistralai/Mixtral-8x7B-Instruct-v0.1",
-    "meta-llama/Meta-Llama-3-70B",
-    "meta-llama/Meta-Llama-3-70B-Instruct",
     "mistralai/Mixtral-8x22B-v0.1",
     "mistralai/Mixtral-8x22B-Instruct-v0.1",
+
+    # Yi models
+    "01-ai/Yi-34B",
+    "01-ai/Yi-34B-Chat",
+
+    # Qwen2 models
+    # "Qwen/Qwen2-1.5B",
+    # "Qwen/Qwen2-1.5B-Instruct",
+    # "Qwen/Qwen2-7B",
+    # "Qwen/Qwen2-7B-Instruct",
+    # "Qwen/Qwen2-72B",
+    # "Qwen/Qwen2-72B-Instruct",
 ]