mirror of
https://github.com/huggingface/lerobot.git
synced 2026-05-19 18:49:52 +00:00
Pepijn
426d48dbbf
pi052 had the same text-CE collapse bug smolvla2 had — PaliGemma's embed_prefix flags the language block att=0, so make_att_2d_masks makes it fully bidirectional and the text cross-entropy degenerates into a copy task. Ported the three model-specific fixes: - _mark_target_span_causal: set att=1 on supervised target language positions so the text-CE is genuine causal next-token prediction. Applied in both _compute_all_losses_fused and _compute_text_and_fast_loss. - flow_loss_weight 10.0 -> 5.0: the paper's a=10 swamps the LM head once the flow-only low_level recipe fires often (matches SmolVLA2Config). - _flatten_say_tool_calls in the text tokenizer: serialize `say` tool calls into a <say>...</say> marker so the spoken reply is tokenized and supervised (PaliGemma's flat prompt has no structured calls, so they were dropped entirely). select_message needed no change: pi052's prefix is [images, language] with no trailing state token, so it already decodes from the last language token. Regression tests mirror the smolvla2 attention-masking + tool-call suite. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>