From 90309ca8dcb06f0611c1bde4a61eb08fb7317993 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Mon, 29 Jan 2024 03:45:07 +1100
Subject: [PATCH] Nightly (#140)

* 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 a208ec46e012cf470ecefe6268a66358215df7b6.

* 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

* Update mistral.py

* attention mask

* Update llama.py

* Update llama.py

* Update mistral.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update dpo.py

* Patch saving

* Update save.py

* Update save.py

* patch_saving_functions

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* print

* Mistral patch

* Update mistral.py

* Update save.py

* saving
---
 unsloth/models/mistral.py | 3 +++
 unsloth/save.py           | 1 -
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/unsloth/models/mistral.py b/unsloth/models/mistral.py
index 2941fb32fb..91a2dd7e35 100644
--- a/unsloth/models/mistral.py
+++ b/unsloth/models/mistral.py
@@ -375,6 +375,9 @@ class FastMistralModel(FastLlamaModel):
         
         # Log Unsloth version for future fastpaths for inference
         model.config.update({"unsloth_version" : __version__})
+
+        # Add save modules
+        patch_saving_functions(model)
         
         return model, tokenizer
     pass
diff --git a/unsloth/save.py b/unsloth/save.py
index baa8f3f5ca..4cda8b9651 100644
--- a/unsloth/save.py
+++ b/unsloth/save.py
@@ -278,7 +278,6 @@ def unsloth_save_model(
         not hasattr(internal_model.model, "layers")
     ):
         # Do general saving
-        print(type(model))
         # Edit save_pretrained_settings
         # [TODO] _create_repo has errors due to **kwargs getting accepted
         for deletion in \