From dc4618ce475554d99fab76daae9746baa62bf090 Mon Sep 17 00:00:00 2001
From: Vineeth Sai <vineethsai4444@gmail.com>
Date: Wed, 8 Jul 2026 13:40:39 -0700
Subject: [PATCH] Fix duplicate unsloth/gemma-2b-bnb-4bit mapper key routing
 the base 4bit repo to the instruct model (#6891)

---
 .github/workflows/consolidated-tests-ci.yml |  1 +
 tests/test_gemma_2b_mapper_key.py           | 46 +++++++++++++++++++++
 unsloth/models/mapper.py                    |  2 +-
 3 files changed, 48 insertions(+), 1 deletion(-)
 create mode 100644 tests/test_gemma_2b_mapper_key.py

diff --git a/.github/workflows/consolidated-tests-ci.yml b/.github/workflows/consolidated-tests-ci.yml
index 6ff3d19ba..1bb4c2bb5 100644
--- a/.github/workflows/consolidated-tests-ci.yml
+++ b/.github/workflows/consolidated-tests-ci.yml
@@ -366,6 +366,7 @@ jobs:
             tests/python/test_fast_language_model_text_only.py \
             tests/test_bad_mappings_redirect.py \
             tests/test_prefetch_snapshot_scope.py \
+            tests/test_gemma_2b_mapper_key.py \
             --deselect 'tests/utils/test_attention_masks.py::test_run_attention_flash_varlen_receives_window_and_softcap'
           # The deselected test monkeypatches flash_attn_varlen_func, which is
           # only bound on the module when `flash_attn` is importable. flash_attn
diff --git a/tests/test_gemma_2b_mapper_key.py b/tests/test_gemma_2b_mapper_key.py
new file mode 100644
index 000000000..31edacfce
--- /dev/null
+++ b/tests/test_gemma_2b_mapper_key.py
@@ -0,0 +1,46 @@
+"""Regression test for the duplicate ``unsloth/gemma-2b-bnb-4bit`` key in
+``unsloth/models/mapper.py``.
+
+The 4bit instruction-tuned Gemma 2B entry was accidentally keyed with the base
+model's repo name, so ``__INT_TO_FLOAT_MAPPER`` held two identical
+``unsloth/gemma-2b-bnb-4bit`` keys. Python keeps only the last value for a
+duplicate literal key, so the base 4bit repo resolved to the *instruct* model,
+the base model lost its reverse (4x-faster) mapping, and
+``unsloth/gemma-2b-it-bnb-4bit`` was never registered at all.
+
+``mapper.py`` has no imports, so we exec it directly and inspect the built
+mappers without importing ``unsloth`` (which requires a GPU).
+"""
+
+import os
+
+MAPPER_PATH = os.path.join(os.path.dirname(__file__), os.pardir, "unsloth", "models", "mapper.py")
+
+
+def _load_mappers():
+    with open(MAPPER_PATH) as f:
+        source = f.read()
+    namespace = {}
+    exec(compile(source, MAPPER_PATH, "exec"), namespace)
+    return namespace
+
+
+def test_gemma_2b_base_and_instruct_4bit_are_distinct():
+    namespace = _load_mappers()
+    int_to_float = namespace["INT_TO_FLOAT_MAPPER"]
+    float_to_int = namespace["FLOAT_TO_INT_MAPPER"]
+
+    # The base 4bit repo must resolve to the base model, not the instruct one.
+    assert int_to_float["unsloth/gemma-2b-bnb-4bit"] == "unsloth/gemma-2b"
+
+    # The instruct 4bit repo must be registered and resolve to the instruct model.
+    assert "unsloth/gemma-2b-it-bnb-4bit" in int_to_float
+    assert int_to_float["unsloth/gemma-2b-it-bnb-4bit"] == "unsloth/gemma-2b-it"
+
+    # The base model must reverse-map back to the base 4bit repo.
+    assert float_to_int["unsloth/gemma-2b"] == "unsloth/gemma-2b-bnb-4bit"
+    assert float_to_int["google/gemma-2b"] == "unsloth/gemma-2b-bnb-4bit"
+
+    # The instruct model must reverse-map to the instruct 4bit repo.
+    assert float_to_int["unsloth/gemma-2b-it"] == "unsloth/gemma-2b-it-bnb-4bit"
+    assert float_to_int["google/gemma-2b-it"] == "unsloth/gemma-2b-it-bnb-4bit"
diff --git a/unsloth/models/mapper.py b/unsloth/models/mapper.py
index 57c1e292c..f3a0e1f9b 100644
--- a/unsloth/models/mapper.py
+++ b/unsloth/models/mapper.py
@@ -134,7 +134,7 @@ __INT_TO_FLOAT_MAPPER = \
         "unsloth/gemma-7b-it",
         "google/gemma-7b-it",
     ),
-    "unsloth/gemma-2b-bnb-4bit" : (
+    "unsloth/gemma-2b-it-bnb-4bit" : (
         "unsloth/gemma-2b-it",
         "google/gemma-2b-it",
     ),