From dd63acf1cc532a161693aa8d529e05bde3282425 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Mon, 11 Nov 2024 18:46:05 -0800
Subject: [PATCH] Qwen 2.5 Coder

---
 unsloth/models/llama.py  |  3 ++-
 unsloth/models/mapper.py | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 7f07bea4c5..47a57024a2 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -2317,7 +2317,8 @@ class FastLlamaModel:
                     layer.self_attn.apply_qkv = apply_lora_qkv
                     n_qkv += 1
                 else:
-                    if model_type != "qwen2":
+                    if model_type == "qwen2": n_qkv += 1
+                    else:
                         logger.warning_once(
                             "Not an error, but Unsloth cannot patch Attention layers with our manual autograd engine since either LoRA adapters\n"\
                             "are not enabled or a bias term (like in Qwen) is used."
diff --git a/unsloth/models/mapper.py b/unsloth/models/mapper.py
index 10e40ab7c6..d4f1278e1d 100644
--- a/unsloth/models/mapper.py
+++ b/unsloth/models/mapper.py
@@ -384,22 +384,54 @@ __INT_TO_FLOAT_MAPPER = \
         "unsloth/Qwen2.5-Math-72B-Instruct",
         "Qwen/Qwen2.5-Math-72B-Instruct",
     ),
+    "unsloth/Qwen2.5-Coder-0.5B-bnb-4bit" : (
+        "unsloth/Qwen2.5-Coder-0.5B",
+        "Qwen/Qwen2.5-Coder-0.5B",
+    ),
     "unsloth/Qwen2.5-Coder-1.5B-bnb-4bit" : (
         "unsloth/Qwen2.5-Coder-1.5B",
         "Qwen/Qwen2.5-Coder-1.5B",
     ),
+    "unsloth/Qwen2.5-Coder-3B-bnb-4bit" : (
+        "unsloth/Qwen2.5-Coder-3B",
+        "Qwen/Qwen2.5-Coder-3B",
+    ),
     "unsloth/Qwen2.5-Coder-7B-bnb-4bit" : (
         "unsloth/Qwen2.5-Coder-7B",
         "Qwen/Qwen2.5-Coder-7B",
     ),
+    "unsloth/Qwen2.5-Coder-14B-bnb-4bit" : (
+        "unsloth/Qwen2.5-Coder-14B",
+        "Qwen/Qwen2.5-Coder-14B",
+    ),
+    "unsloth/Qwen2.5-Coder-32B-bnb-4bit" : (
+        "unsloth/Qwen2.5-Coder-32B",
+        "Qwen/Qwen2.5-Coder-32B",
+    ),
+    "unsloth/Qwen2.5-Coder-0.5B-Instruct-bnb-4bit" : (
+        "unsloth/Qwen2.5-Coder-Instruct-0.5B",
+        "Qwen/Qwen2.5-Coder-Instruct-0.5B",
+    ),
     "unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit" : (
         "unsloth/Qwen2.5-Coder-Instruct-1.5B",
         "Qwen/Qwen2.5-Coder-Instruct-1.5B",
     ),
+    "unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit" : (
+        "unsloth/Qwen2.5-Coder-3B-Instruct",
+        "Qwen/Qwen2.5-Coder-3B-Instruct",
+    ),
     "unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit" : (
         "unsloth/Qwen2.5-Coder-7B-Instruct",
         "Qwen/Qwen2.5-Coder-7B-Instruct",
     ),
+    "unsloth/Qwen2.5-Coder-14B-Instruct-bnb-4bit" : (
+        "unsloth/Qwen2.5-Coder-14B-Instruct",
+        "Qwen/Qwen2.5-Coder-14B-Instruct",
+    ),
+    "unsloth/Qwen2.5-Coder-32B-Instruct-bnb-4bit" : (
+        "unsloth/Qwen2.5-Coder-32B-Instruct",
+        "Qwen/Qwen2.5-Coder-32B-Instruct",
+    ),
     "unsloth/Llama-3.2-1B-bnb-4bit" : (
         "unsloth/Llama-3.2-1B",
         "meta-llama/Llama-3.2-1B",