From 13a7cbf3b76b0d0a00272c0153878f15e02ff606 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Sun, 17 Mar 2024 22:09:50 +1100
Subject: [PATCH] Bug fixes (#257)

* Update gemma.py

* Update llama.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update cross_entropy_loss.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* rope

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* llama

* Update llama.py

* gemma

* 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

* 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

* Update cross_entropy_loss.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update save.py

* RoPE

* Update llama.py

* Update llama.py

* Update llama.py

* Update gemma.py

* correct_dtype

* Update gemma.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Chat Templates

* Update README.md

* Update README.md

* Update llama.py

* DoRA

* Update _utils.py

* Update chat_templates.py

* Update llama.py

* Hotfix - fix DoRA, Gemma prompt template (#202) (#203)

* Update save.py

* saving

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update __init__.py

* Update save.py

* Update save.py

* Update save.py

* save

* trainer

* spaces

* original

* Gemma

* Update pyproject.toml

* Update mapper.py

* Update fast_lora.py

* FastGemmaModel

* model_type

* Update llama.py

* Update llama.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update llama.py

* Update fast_lora.py

* Update llama.py

* Update llama.py

* Update cross_entropy_loss.py

* Update llama.py

* Update llama.py

* gemma

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update fast_lora.py

* Update fast_lora.py

* Fast CE Loss

* 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 llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* CE

* Update llama.py

* Update llama.py

* Update cross_entropy_loss.py

* Update geglu.py

* Update cross_entropy_loss.py

* revert

* Update llama.py

* Update llama.py

* norm

* Update gemma.py

* Update gemma.py

* position_ids

* Update gemma.py

* Update gemma.py

* pos

* Update llama.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update cross_entropy_loss.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* revert

* revert

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update cross_entropy_loss.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* rope

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* llama

* Update llama.py

* gemma

* 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

* 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

* Update cross_entropy_loss.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update save.py

* RoPE

* Update llama.py

* Update llama.py

* Update llama.py

* Update gemma.py

* correct_dtype

* Update gemma.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Chat Templates

* Update README.md

* Update README.md

* Update llama.py

* DoRA

* Update _utils.py

* Update chat_templates.py

* Update pyproject.toml

* Small fixes

* Update pyproject.toml

* Approx gelu

* Update geglu.py

* Approx gelu

* Update llama.py

* Update __init__.py

* Update __init__.py

* Update _utils.py

* Update geglu.py

* Update gemma.py

* Update rms_layernorm.py

* Update rms_layernorm.py

* Update rms_layernorm.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Fix Gemma merging

* Update rms_layernorm.py

* Update gemma.py

* Update pyproject.toml

* Layernorms

* Gemma precision

* Update gemma.py

* sqrt

* Update gemma.py

* Update save.py

* RoPE and Gemma precision

* Update rms_layernorm.py

* Fix warning

* Update chat_templates.py

* Update chat_templates.py

* Update save.py

* Update save.py

* Update save.py

* Update chat_templates.py

* Update llama.py

* model_name

* Update loader.py

* Tokenizer overwritten

* Update llama.py

* Update llama.py

* Update llama.py

* Update save.py

* Accuracy

* Revert

* Update save.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update fast_lora.py

* Update chat_templates.py

* Update save.py

* Update save.py

* Update llama.py

* Update llama.py

* Account for DoRA

* Update llama.py

* Update save.py

* GGUF incorrect

* Update save.py

* Update pyproject.toml

* kaggle new

* Update pyproject.toml

* Update pyproject.toml

* upcasting

* Fix Colab

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update chat_templates.py

* Update chat_templates.py

* Update chat_templates.py

* Update chat_templates.py

* Update chat_templates.py

* Update pyproject.toml

* Update pyproject.toml

* Update pyproject.toml

* Update rope_embedding.py

* Update rope_embedding.py

* Fix bugs

* Update fast_lora.py

* Update fast_lora.py

* Update README.md

* Update README.md

* GGUF

* Update save.py

* Update save.py

* Update save.py

* Update save.py

* Update README.md

* Update README.md

* Bugs

* Update fast_lora.py

* Update pyproject.toml

* Update fast_lora.py
---
 pyproject.toml  |  3 +++
 unsloth/save.py | 10 ++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 3ea50ca00e..324e01157b 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -178,6 +178,9 @@ colab-no-deps = [
     "xformers",
     "bitsandbytes",
 ]
+colab = [
+    "unsloth[cu121]",
+]
 colab-ampere = [
     "unsloth[colab-ampere-torch220]",
     "packaging",
diff --git a/unsloth/save.py b/unsloth/save.py
index 05ff748db2..5970d74d11 100644
--- a/unsloth/save.py
+++ b/unsloth/save.py
@@ -684,6 +684,9 @@ def save_to_gguf(
 ):
     from transformers.models.llama.modeling_llama import logger
 
+    if quantization_method.startswith("iq2"):
+        raise RuntimeError("Unsloth: Currently iq2 type quantizations aren't supported yet - sorry!")
+
     # Careful convert.py is only for Llama / Mistral based archs
     use_fast_convert = False
     if   model_type == "llama":   use_fast_convert = True
@@ -743,8 +746,11 @@ def save_to_gguf(
         if   first_conversion == "f32" : pass
         elif first_conversion == "f16" : pass
         elif first_conversion == "q8_0":
-            logger.warning_once("Unsloth: We must use f16 for quantization first.")
-            first_conversion = "f16"
+            logger.warning_once(
+                "Unsloth: Using q8_0 for the `first_conversion` will lose a bit of accuracy, "\
+                "but saves disk space!"
+            )
+            # first_conversion = "f16"
         pass
     pass