diff --git a/unsloth/models/loader.py b/unsloth/models/loader.py index fb97e74622..377f595280 100644 --- a/unsloth/models/loader.py +++ b/unsloth/models/loader.py @@ -347,10 +347,11 @@ class FastVisionModel(FastBaseVisionModel): use_gradient_checkpointing = "unsloth", resize_model_vocab = None, # [TODO] No effect revision = None, + return_logits = False, # Return logits *args, **kwargs, ): if token is None: token = get_token() - + patch_compiled_autograd() patch_compiling_bitsandbytes() if use_gradient_checkpointing == "unsloth": @@ -359,30 +360,31 @@ class FastVisionModel(FastBaseVisionModel): old_model_name = model_name model_name = get_model_name(model_name, load_in_4bit) - # with contextlib.redirect_stdout(open(os.devnull, "w")): - patch_loss_functions(torch_compile = False) - model_types = unsloth_compile_transformers( - model_name = model_name, - sdpa_dynamic_mask = True, - sdpa_bool_masks = True, - sdpa_gqa_replace = True, - sdpa_dynamic_compile = True, - compile_attention = True, - disable_causal_masks = True, - compile_torch_modules = True, - compile_custom_modules = True, - compile_function_calls = True, - fuse_lm_head = True, - gradient_checkpointing = True, - manual_replacements = True, - epilogue_fusion = True, - max_autotune = False, - shape_padding = True, - cudagraphs = False, - debug = False, - import_from_cache = False, - disable = False, - ) + with contextlib.redirect_stdout(open(os.devnull, "w")): + patch_loss_functions(torch_compile = False) + model_types = unsloth_compile_transformers( + model_name = model_name, + sdpa_dynamic_mask = True, + sdpa_bool_masks = True, + sdpa_gqa_replace = True, + sdpa_dynamic_compile = True, + compile_attention = True, + disable_causal_masks = True, + compile_torch_modules = True, + compile_custom_modules = True, + compile_function_calls = True, + fuse_lm_head = True, + gradient_checkpointing = True, + manual_replacements = True, + epilogue_fusion = True, + max_autotune = False, + shape_padding = True, + cudagraphs = False, + debug = False, + import_from_cache = False, + disable = False, + return_logits = return_logits, + ) pass # First check if it's a normal model via AutoConfig