SmolVLM forward with images fails in v5.20.1: shape '[-1, 14, ...]' is invalid (inputs_merger uses vision patch_size)
Public issue #49724 in huggingface/transformers. The source issue contains the full report and discussion.
Read original source![Source page screenshot: SmolVLM forward with images fails in v5.20.1: shape '[-1, 14, ...]' is invalid (inputs_merger uses vision patch_size)](/media/94e803b9c22fea5550bca5b8?v=2026-11-07T13%3A15%3A28.855Z)
Source record
Research analysis
Reported problem
The record contains the title “SmolVLM forward with images fails in v5.20.1: shape '[-1, 14, ...]' is invalid (inputs_merger uses vision patch_size)” but no substantive source summary.
Frequency & alternatives
Recent records to compare: “Gemma3 under Flash Attention silently drops the bidirectional attention over image tokens” (GitHub Issues, Nov 13, 2026); “Add a PIL backend for Gemma4UnifiedImageProcessor (Gemma 4 12B)” (GitHub Issues, Nov 12, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Demand hypothesis
Treat the reported task or obstacle as an interview lead. A feature request, complaint or search for alternatives does not by itself identify a budget owner or willingness to pay.
Commercial evidence gaps
Missing evidence: distinct affected users, repeated occasions, current workaround, measured time or money cost, purchasing authority and a response to a concrete offer.
Validation decision
Group original reports by the same task and deduplicate authors and reposts. Ask how the task is handled today and what it costs; test a defined offer before claiming paid demand.