From 8bea94c1370e2f6fa8eb28236a21a5a4b4dd0a0b Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Sun, 10 Mar 2024 20:09:34 +1100
Subject: [PATCH] Saving fixes (#231)

* 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 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
---
 unsloth/models/llama.py | 28 +++++++++++++---------------
 unsloth/save.py         |  8 ++++----
 2 files changed, 17 insertions(+), 19 deletions(-)

diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 6ed52a7acb..30348b69c2 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -705,26 +705,24 @@ def CausalLM_fast_forward(fast_forward_inference):
         *args, **kwargs,
     ) -> Union[Tuple, CausalLMOutputWithPast]:
 
-        if causal_mask is None and past_key_values is None:
-            causal_mask = xformers.attn_bias.LowerTriangularMask()
-
-        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
-        output_hidden_states = (
-            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
-        )
-        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
-
-        # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
-        self.model._has_no_labels = labels is None
-
-        if past_key_values is not None and \
-            hasattr(self.model.layers[0].self_attn, "paged_attention"):
+        if past_key_values is not None and hasattr(self.model.layers[0].self_attn, "paged_attention"):
             outputs = fast_forward_inference(
                 self.model,
                 input_ids,
                 past_key_values,
             )
         else:
+            causal_mask = xformers.attn_bias.LowerTriangularMask()
+    
+            output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+            output_hidden_states = (
+                output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+            )
+            return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+            # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
+            self.model._has_no_labels = labels is None
+
             outputs = self.model(
                 input_ids=input_ids,
                 causal_mask=causal_mask,
@@ -988,7 +986,7 @@ class FastLlamaModel:
             padding_side     = "right",
             token            = token,
         )
-        
+
         model, tokenizer = patch_tokenizer(model, tokenizer)
         model = model_patcher.post_patch(model)
 
diff --git a/unsloth/save.py b/unsloth/save.py
index 5971d76e6e..42d326e128 100644
--- a/unsloth/save.py
+++ b/unsloth/save.py
@@ -90,14 +90,14 @@ def _merge_lora(layer, name):
             W = fast_dequantize(W, quant_state)
         else:
             dtype = W.dtype
-        W = W.to(torch.float32).t()
-        # W = W.t()
+        # W = W.to(torch.float32).t()
+        W = W.t()
 
         if A is not None:
             # sAB = (A.t().to(torch.float32) @ (s * B.t().to(torch.float32)))
             # W += sAB
-            W.addmm_(A.t().to(torch.float32), B.t().to(torch.float32), alpha = s)
-            # W.addmm_(A.t().to(W.dtype), B.t().to(W.dtype), alpha = s)
+            # W.addmm_(A.t().to(torch.float32), B.t().to(torch.float32), alpha = s)
+            W.addmm_(A.t().to(W.dtype), B.t().to(W.dtype), alpha = s)
             # if not torch.isfinite(W).all():
             maximum_element = torch.max(W.min().abs(), W.max())
             if not torch.isfinite(maximum_element).item():