From de60e88b6bd98c8fc2060682099e6b9108e14210 Mon Sep 17 00:00:00 2001 From: githubnemo Date: Wed, 3 Sep 2025 18:37:52 +0200 Subject: [PATCH] Fix missing code start in docs (#2768) There was a minor typo which a suggestion of PR #2609 which broke code formatting for one code sample. This is a simple fix for that. --- docs/source/developer_guides/lora.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/docs/source/developer_guides/lora.md b/docs/source/developer_guides/lora.md index b2049f61..214ef654 100644 --- a/docs/source/developer_guides/lora.md +++ b/docs/source/developer_guides/lora.md @@ -248,7 +248,10 @@ output = model_alora.generate(**inputs_alora, past_key_values=cache) output_text_alora = tokenizer.decode(output[0]) # Note: cache is now tainted with adapter values and cannot be used in base model from here on! +``` + **Pattern 2: aLoRA generation followed by base model (or another aLoRA) with partial context overlap** Here, we prefill the shared context using the base model, and then generate. + ``` from transformers import DynamicCache import copy