From 9bc260938ce2bc1e818e7e3cc40e84bc312bfb66 Mon Sep 17 00:00:00 2001 From: Zewen Shen Date: Thu, 5 Dec 2024 02:54:18 -0500 Subject: [PATCH] Fix vision model tokenizer padding side. (#1384) * Dynamic quants (#1379) * typing * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * int64 * Update _utils.py * Update cross_entropy_loss.py * constexpr * constexpr * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update _utils.py * Update _utils.py * Update _utils.py * CE * Update cross_entropy_loss.py * Update _utils.py * Update llama.py * Update _utils.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update utils.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * typing * Update rope_embedding.py * types * Disable compiling * Update _utils.py * Update _utils.py * Forward hook * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Update llama.py * Update _utils.py * Update pyproject.toml * Update _utils.py * Update llama.py * CE Loss * Update cross_entropy_loss.py * Update _utils.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update llama.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Fix: cast logits to float32 in cross_entropy_forward to prevent errors (#1254) * Fix: cast logits to float32 in cross_entropy_forward to prevent errors * Update cross_entropy_loss.py --------- Co-authored-by: Daniel Han * Throw error when inferencing longer than max_popsition_embeddings (#1236) * Throw error when inferencing longer than max_popsition_embeddings without rope scaling * Update llama.py --------- Co-authored-by: Daniel Han * CLI now handles user input strings for dtype correctly (#1235) Co-authored-by: root * Update flex_attention.py * Update _utils.py * Update _utils.py * Update flex_attention.py * Update flex_attention.py * Update loader.py * Update loader.py * Update flex_attention.py * Update flex_attention.py * Update flex_attention.py * Update flex_attention.py * Update _utils.py * Update cross_entropy_loss.py * Update _utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * triton_cast * Update utils.py * Qwen 2.5 Coder * Fix/export mistral (#1281) * Enhance install_python_non_blocking to handle protobuf installation and process management * Revert "Enhance install_python_non_blocking to handle protobuf installation and process management" This reverts commit f09974b151df1a6ce4708bc4cf75e5eb6b024aed. * Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION to 'python' to address issue #1266 * Revert "Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION to 'python' to address issue #1266" This reverts commit 9fc130785dac65e9469306f71c666c155add53f1. * Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION to 'python' to address issue #1266 * Update __init__.py --------- Co-authored-by: Daniel Han * DOC Update - Update README.md with os.environ in example (#1269) * Update README.md with os.environ in example Added OS Environ in example to avoid device conflicts , for a user at least in jupyter notebook this allows to select GPU in a multi GPU setup. As currently the unsloth init checks all GPU's and takes the first in the order which can be a issue when some GPU's are in use and the list still shows them. So to manually avoid this, this os config is required. Small change but a bit time saver for those who straight away copies the tutorials * Update README.md --------- Co-authored-by: Daniel Han * fix/get_chat_template (#1246) * Refactor `get_chat_template` to now support system message instead. It supposed to fix ollama tokenizer chattemplate to * Remove type hinting * Update chat_templates.py --------- Co-authored-by: Daniel Han * fix/sft-trainer (#1276) * Add patch for SFTTrainer to maintain backward compatibility with TRL changes * Update trainer.py * Update trainer.py * Refactor trainer patch to maintain backward compatibility with TRL changes * Update trainer.py * Refactor trainer.py to exclude non-convertible trainers from backward compatibility patch --------- Co-authored-by: Daniel Han * Update __init__.py * Update trainer.py * Update trainer.py * Update trainer.py * Update tokenizer_utils.py * Update llama.py * Fix #853 * fix/sfttrainer-compatibility (#1293) * Refactor trainer.py to import SFTConfig directly and update UnslothTrainingArguments class inheritance * Update trainer.py * Update trainer.py --------- Co-authored-by: Daniel Han * Update rms_layernorm.py * Update rms_layernorm.py * Gemma * Update rms_layernorm.py * Update gemma2.py * Cut Cross Entropy * Update llama.py * Cut Cross Entropy * Update llama.py * Update llama.py * Update llama.py * Update __init__.py * Update __init__.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update mapper.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * patch_fast_lora * vision * Update fast_lora.py * Update _utils.py * Update _utils.py * Vision * Update trainer.py * Update save.py * FastBaseVisionModel * Update loader_utils.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update vision.py * Update _utils.py * tokenizer_name * Update loader.py * Update vision.py * Update save.py * Update save.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update _utils.py * Update loader.py * kwargs * logits * Update llama.py * Update llama.py * Update llama.py * Update _utils.py * Update _utils.py * Update _utils.py * error * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update loader.py * Update llama.py * Update vision.py * Update loader.py * Old torch versions * Update loader.py * Update loader.py * prints * recheck * Update loader.py * Update loader.py * Update _utils.py * Update _utils.py * Update mapper.py * Feat/kto (#1316) * Add PatchKTOTrainer and update model imports * Update dpo.py * Update __init__.py * Delete unsloth/models/kto.py --------- Co-authored-by: Daniel Han * Fix orpo/dpo trainer (#1286) * change the colab notebook for dpo zephyr and orpo * use original tokenizer * Update README.md * Update README.md --------- Co-authored-by: Daniel Han * skip modules * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Fix llama.cpp * Update save.py * Update save.py * Update vision.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update _utils.py * Update save.py * Update save.py * Update mapper.py * modules --------- Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com> Co-authored-by: Datta Nimmaturi Co-authored-by: Edwin Fennell Co-authored-by: root Co-authored-by: Uday Girish Maradana Co-authored-by: cell-dame <122996026+dame-cell@users.noreply.github.com> * Update README.md Unsloth Dynamic 4-bit Quantization Update * Fix vision model tokenizer padding side. * Update vision.py --------- Co-authored-by: Daniel Han Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com> Co-authored-by: Datta Nimmaturi Co-authored-by: Edwin Fennell Co-authored-by: root Co-authored-by: Uday Girish Maradana Co-authored-by: cell-dame <122996026+dame-cell@users.noreply.github.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> --- unsloth/models/vision.py | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/unsloth/models/vision.py b/unsloth/models/vision.py index 0f682c6b40..a8ef9c0416 100644 --- a/unsloth/models/vision.py +++ b/unsloth/models/vision.py @@ -164,6 +164,8 @@ class FastBaseVisionModel: padding_side = "right", token = token, ) + # Add padding side as well + tokenizer.tokenizer.padding_side = "right" model, tokenizer = patch_tokenizer(model, tokenizer) model = post_patch_loss_function(model) @@ -187,6 +189,7 @@ class FastBaseVisionModel: # Save tokenizer for inference purposes tokenizer.padding_side = "left" # Force inference + tokenizer.tokenizer.padding_side = "left" # Force inference internal_model = model while hasattr(internal_model, "model"): internal_model._saved_temp_tokenizer = tokenizer @@ -315,12 +318,12 @@ class FastBaseVisionModel: internal_model = model while hasattr(internal_model, "model"): if hasattr(internal_model, "_saved_temp_tokenizer"): - internal_model._saved_temp_tokenizer.padding_side = "right" + internal_model._saved_temp_tokenizer.tokenizer.padding_side = "right" pass internal_model = internal_model.model pass if hasattr(internal_model, "_saved_temp_tokenizer"): - internal_model._saved_temp_tokenizer.padding_side = "right" + internal_model._saved_temp_tokenizer.tokenizer.padding_side = "right" pass # Clear deleted GPU items @@ -361,12 +364,12 @@ class FastBaseVisionModel: internal_model = model while hasattr(internal_model, "model"): if hasattr(internal_model, "_saved_temp_tokenizer"): - internal_model._saved_temp_tokenizer.padding_side = "left" + internal_model._saved_temp_tokenizer.tokenizer.padding_side = "left" pass internal_model = internal_model.model pass if hasattr(internal_model, "_saved_temp_tokenizer"): - internal_model._saved_temp_tokenizer.padding_side = "left" + internal_model._saved_temp_tokenizer.tokenizer.padding_side = "left" pass # Also disable training for embeddings for NEFTune @@ -405,12 +408,12 @@ class FastBaseVisionModel: internal_model = model while hasattr(internal_model, "model"): if hasattr(internal_model, "_saved_temp_tokenizer"): - internal_model._saved_temp_tokenizer.padding_side = "right" + internal_model._saved_temp_tokenizer.tokenizer.padding_side = "right" pass internal_model = internal_model.model pass if hasattr(internal_model, "_saved_temp_tokenizer"): - internal_model._saved_temp_tokenizer.padding_side = "right" + internal_model._saved_temp_tokenizer.tokenizer.padding_side = "right" pass # Also re-enable training for embeddings for NEFTune