diff --git a/README.md b/README.md
index 422abcf3b8..a348e48143 100644
--- a/README.md
+++ b/README.md
@@ -7,7 +7,7 @@
 ## 2-5x faster 60% less memory local QLoRA finetuning
 * Supports Llama 7b, 13b, 70b, CodeLlama 34b, Mistral 7b, TinyLlama and all Llama archs!
 * Llama 7b [Colab T4 example](https://colab.research.google.com/drive/1n-fgduZhRUsSjgpqNtVkXA3rSfE7iBdg?usp=sharing) on 1 T4 2x faster, uses 43% less VRAM (8.4GB) LAION dataset. [Alpaca T4 example](https://colab.research.google.com/drive/1oW55fBmwzCOrBVX66RcpptL3a99qWBxb?usp=sharing) 2x faster on 1 T4, using 6.4GB VRAM.
-* Mistral 7b [Colab A100 example](https://colab.research.google.com/drive/1SKrKGV-BZoU4kv5q3g0jtE_OhRgPtrrQ?usp=sharing) on 1 A100 2.2x faster, uses 62% less VRAM (12.4GB).
+* Mistral 7b [Colab A100 example](https://colab.research.google.com/drive/1SKrKGV-BZoU4kv5q3g0jtE_OhRgPtrrQ?usp=sharing) on 1 A100 2.2x faster, uses 62% less VRAM (12.4GB). [Colab T4 example](https://colab.research.google.com/drive/15pyLgRN97B_jA56HS0esx56knA9I5tuv?usp=sharing)
 * CodeLlama 34b [Colab example](https://colab.research.google.com/drive/1gdHyAx8XJsz2yNV-DHvbHjR1iCef5Qmh?usp=sharing) does not OOM is 1.9x faster, uses 32% less VRAM (27GB).
 * Kaggle 2 Tesla T4s 5.28x faster on Alpaca. [Kaggle example](https://www.kaggle.com/danielhanchen/unsloth-laion-t4-ddp)
 * All kernels written in [OpenAI's Triton](https://openai.com/research/triton) language.
diff --git a/unsloth/models/mistral.py b/unsloth/models/mistral.py
index 8b1fd0fd84..7eb651cd33 100644
--- a/unsloth/models/mistral.py
+++ b/unsloth/models/mistral.py
@@ -37,6 +37,17 @@ def MistralAttention_fast_forward(
     bsz, q_len, _ = hidden_states.size()
     Q, K, V = self.apply_qkv(self, hidden_states)
 
+    # Check for inference
+    if use_cache and past_key_value is not None and q_len == 1:
+        A, past_key_value = LlamaAttention_fast_forward_inference(
+            self,
+            hidden_states,
+            past_key_value,
+            position_ids,
+        )
+        return A, None, past_key_value
+    pass
+
     n_heads    = self.num_heads
     n_groups   = self.num_key_value_groups
     n_kv_heads = self.num_key_value_heads
@@ -152,8 +163,10 @@ def MistralForCausalLM_fast_forward(
         elif q_len <= sliding_window:
             causal_mask = xformers.attn_bias.LowerTriangularMask()
         else:
-            causal_mask = xformers.attn_bias.BlockDiagonalCausalLocalAttentionMask.\
-                make_local_attention(window_size = sliding_window)
+            # Fix from https://github.com/Rypo
+            causal_mask = xformers.attn_bias.BlockDiagonalCausalMask\
+                .from_seqlens([qlen]*bsz)\
+                .make_local_attention(window_size = sliding_window)
     pass
 
     output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions