mirror of
https://github.com/elder-plinius/OBLITERATUS.git
synced 2026-08-18 00:47:23 +02:00
Brian Bell
84b97f6620
Loading custom-architecture checkpoints (Nemotron Omni family) against transformers 5.14 surfaced API drift and wrapper mismatches: - flash_attention_2 pinned in config but flash-attn not installed: recursively fall back to eager attention, incl. nested sub-configs (multimodal llm_config). - all_tied_weights_keys shim: expected by the accelerate device-map integration and assigned by 5.x post_init, but absent on older remote code. Settable property aggregating legacy _tied_weights_keys, filtering keys that don't resolve on multimodal wrappers. - prepare_inputs_for_generation: 5.x may pass cache_position=None; older remote code assumes a tensor. Wrap and synthesize it. - Legacy list-style _tied_weights_keys normalized post-load so save_pretrained works (emptied when tie_word_embeddings is false). - Multimodal wrappers whose forward() requires media inputs are unwrapped to their language_model submodule for text-only surgery. - Register nemotron_h architecture (hybrid Mamba/attention/MoE, all layer content under layer.mixer) in strategies/utils.py.