NMFW-464 Nemotron VLM hetero mock training

examples/mimo/blend_files/1t_phase1var_moresft_wrapper.yaml

@@ -0,0 +1,6 @@
+# RKarimi 3B-nano SOTA 1T text subset blend.
+# The 3B-nano baseline uses TRAIN_SAMPLES=122070313 and SEQ_LEN=8192,
+# which is 1,000,000,004,096 tokens.
+__module__: megatron.energon
+__class__: McoreBlend
+mcore_json: /scratch/fsw/portfolios/llmservice/projects/llmservice_fm_text/users/rkarimimahab/workspace/blends/1T-phase1var-moresft.json

examples/mimo/blend_files/text_only_1t_hel.yaml

@@ -0,0 +1,8 @@
+# HEL text-only Energon blend for MIMO jitter isolation.
+__module__: megatron.energon
+__class__: MetadatasetV2
+splits:
+  train:
+    blend:
+    - weight: 1.0
+      path: __MEGATRON_ROOT__/examples/mimo/blend_files/1t_phase1var_moresft_wrapper.yaml

examples/mimo/data/__init__.py

@@ -1,5 +1,11 @@
-from .energon_avlm_task_encoder import VisionAudioQASample
+"""MIMO data providers and task encoders."""
 
-all = [
-    VisionAudioQASample,
-]
+__all__ = ["VisionAudioQASample"]
+
+
+def __getattr__(name):
+    if name == "VisionAudioQASample":
+        from .energon_avlm_task_encoder import VisionAudioQASample
+
+        return VisionAudioQASample
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")