Add multimodal support

src/display/about.py

@@ -13,6 +13,7 @@ icons = f"""
 - {ModelType.FT.to_str(" : ")} model: pretrained models finetuned on more data
 - {ModelType.chat.to_str(" : ")} model: chat like fine-tunes, either using IFT (datasets of task instruction), RLHF or DPO (changing the model loss a bit with an added policy), etc
 - {ModelType.merges.to_str(" : ")} model: merges or MoErges, models which have been merged or fused without additional fine-tuning. 
+- {ModelType.MM.to_str(" : ")} model: models integrating multiple data types (e.g., text, image, audio) for tasks like image captioning and visual question answering.
 """
 LLM_BENCHMARKS_TEXT = """
 ## ABOUT

src/display/utils.py

@@ -196,6 +196,7 @@ class ModelType(Enum):
     PT = ModelDetails(name="🟢 pretrained", symbol="🟢")
     CPT = ModelDetails(name="🟩 continuously pretrained", symbol="🟩")
     FT = ModelDetails(name="🔶 fine-tuned on domain-specific datasets", symbol="🔶")
+    MM = ModelDetails(name="🌸 multimodal", symbol="🌸")
     chat = ModelDetails(name="💬 chat models (RLHF, DPO, IFT, ...)", symbol="💬")
     merges = ModelDetails(name="🤝 base merges and moerges", symbol="🤝")
     Unknown = ModelDetails(name="❓ other", symbol="❓")
@@ -215,9 +216,10 @@ class ModelType(Enum):
             return ModelType.chat
         if "merge" in m_type or "🤝" in m_type:
             return ModelType.merges
+        if "multimodal" in m_type or "🌸" in m_type:
+            return ModelType.MM
         return ModelType.Unknown
 
-
 class WeightType(Enum):
     Adapter = ModelDetails("Adapter")
     Original = ModelDetails("Original")