add nv_dpo conversation to accomendate empty system message

Signed-off-by: HuiyingLi <[email protected]>
NVIDIA · Feb 8, 2024 · b0f966d · b0f966d
1 parent 80f8465
commit b0f966d
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 3 deletions.
diff --git a/nemo/collections/multimodal/data/neva/conversation.py b/nemo/collections/multimodal/data/neva/conversation.py
@@ -263,6 +263,17 @@ def dict(self):
     sep2=f"{DEFAULT_SYSTEM_TOKEN}System\n",
 )
 
+conv_nv_dpo = Conversation(
+    system="\n",
+    roles=("User", "Assistant"),
+    version="nv_dpo",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.NVGPT,
+    sep=DEFAULT_SEPARATOR_TOKEN,
+    sep2=f"{DEFAULT_SYSTEM_TOKEN}System\n",
+)
+
 conv_vicuna_v0 = Conversation(
     system="A chat between a curious human and an artificial intelligence assistant. "
     "The assistant gives helpful, detailed, and polite answers to the human's questions.",
@@ -400,8 +411,8 @@ def dict(self):
     "v1_mmtag": conv_llava_v1_mmtag,
     "llava_llama_2": conv_llava_llama_2,
     "nvgpt": conv_nvgpt,
-    "nv_dpo": conv_nvgpt,
-    "nv_steerlm": conv_nvgpt
+    "nv_steerlm": conv_nvgpt,
+    "nv_dpo": conv_nv_dpo,
 }
 
 

diff --git a/nemo/collections/multimodal/data/neva/neva_dataset.py b/nemo/collections/multimodal/data/neva/neva_dataset.py
@@ -487,7 +487,7 @@ def preprocess_nv_dpo(sources: dict, tokenizer, cfg,) -> Dict:
     """<extra_id_0>System\n\n<extra_id_1>User\n{user input}\n<extra_id_1>Assistant\n"""
 
 
-    conv = conversation_lib.conv_nvgpt.copy()
+    conv = conversation_lib.conv_nv_dpo.copy()
 
     # Apply prompt templates
     conversations = []