From b4b50c82b3ea2f731052912e3edec388af39b8b2 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Sun, 28 Jan 2024 04:30:29 +1100
Subject: [PATCH] 1 more bug (#138)

* faster saving & inference

* Update llama.py

* Update save.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update mistral.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* fast inference

* Update llama.py

* Update save.py

* Update llama.py

* Mistral correct RoPE scaling

* Max sequence lengths

* Apache 2

* fast_linear_forward

* Update utils.py

* Update utils.py

* No print

* Update utils.py

* Update utils.py

* inference

* Update llama.py

* Fast inference RoPE

* Update llama.py

* Update llama.py

* RoPE

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* LoRA

* Fast LoRA saving

* Update llama.py

* hidden_states

* q_len == 1

* q_len issue

* Update mistral.py

* Update mistral.py

* incorrect inference

* Update to transformers 4.37

* Graceful FA2 error + torch 2.1.1

* Update mapper.py

* Update pyproject.toml

* Fix saving and bnb-4bit

* Update fast_lora.py

* Update fast_lora.py

* remove patching

* Update llama.py

* Update llama.py

* Update swiglu.py

* Repatch

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update llama.py

* Update fast_lora.py

* Update llama.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update swiglu.py

* Update fast_lora.py

* Update swiglu.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update save.py

* Update fast_lora.py

* Update utils.py

* Update llama.py

* Update fast_lora.py

* Update swiglu.py

* Update save.py

* Update save.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Revert "Update llama.py"

This reverts commit 9c9dc55bef7e71960bd48941e987e8b6239d6783.

* Update llama.py

* Works?

* Update pyproject.toml

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Swiglu

* Update swiglu.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update swiglu.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* attention_mask

* Update llama.py

* Update llama.py

* labels

* Update mistral.py

* Update llama.py

* attention mask

* Update save.py

* Update save.py
---
 unsloth/save.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/unsloth/save.py b/unsloth/save.py
index 471897c0ad..744ec48327 100644
--- a/unsloth/save.py
+++ b/unsloth/save.py
@@ -80,7 +80,8 @@ def _merge_lora(layer, name):
         if quant_state is not None:
             dtype = quant_state.dtype if type(quant_state) is not list else quant_state[2]
             W = fast_dequantize(W, quant_state)
-        pass
+        else:
+            dtype = W.dtype
         W = W.to(torch.float32).t()
 
         if A is not None: