Bug fixes (#3017)

* Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634a. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning
2025-07-21 05:30:14 -07:00 · 2025-07-21 05:30:14 -07:00 · 80e7af5b9f
commit 80e7af5b9f
parent 580b5bca11
4 changed files with 63 additions and 24 deletions
--- a/pyproject.toml
+++ b/pyproject.toml
@ -37,7 +37,7 @@ triton = [
 ]

 huggingface = [
-    "unsloth_zoo>=2025.7.7",
+    "unsloth_zoo>=2025.7.8",
    "packaging",
    "tyro",
    "transformers>=4.51.3,!=4.47.0,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3,!=4.53.0",
@ -381,7 +381,7 @@ colab-ampere-torch220 = [
    "flash-attn>=2.6.3",
 ]
 colab-new = [
-    "unsloth_zoo>=2025.7.7",
+    "unsloth_zoo>=2025.7.8",
    "packaging",
    "tyro",
    "transformers>=4.51.3,!=4.47.0,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3,!=4.53.0",
--- a/unsloth/dataprep/synthetic.py
+++ b/unsloth/dataprep/synthetic.py
@ -80,6 +80,10 @@ class SyntheticDataKit:
        )
        if "dtype" in engine_args:
            dtype_val = engine_args["dtype"]
+            if   dtype_val == torch.float16:  dtype_val = "float16"
+            elif dtype_val == torch.bfloat16: dtype_val = "bfloat16"
+            elif dtype_val == torch.float32:  dtype_val = "float32"
+            engine_args["dtype"] = dtype_val
            # Convert torch.bfloat16, torch.float16, etc. to valid CLI string
            if hasattr(dtype_val, "name"):
                engine_args["dtype"] = dtype_val.name
--- a/unsloth/models/_utils.py
+++ b/unsloth/models/_utils.py
@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.

-__version__ = "2025.7.5"
+__version__ = "2025.7.6"

 __all__ = [
    "SUPPORTS_BFLOAT16",
--- a/unsloth/save.py
+++ b/unsloth/save.py
@ -2240,6 +2240,7 @@ from unsloth_zoo.llama_cpp import (
 def save_to_gguf_generic(
    model,
    save_directory,
+    quantization_method = None,
    quantization_type = "Q8_0",
    repo_id = None,
    token = None,
@ -2252,29 +2253,63 @@ def save_to_gguf_generic(
        install_llama_cpp(just_clone_repo = True)
    pass

-    metadata = _convert_to_gguf(
-        save_directory,
-        print_output = True,
-        quantization_type = quantization_type,
-    )
-    if repo_id is not None:
-        prepare_saving(
-            model,
-            repo_id,
-            push_to_hub = True,
-            max_shard_size = "50GB",
-            private = True,
-            token = token,
-        )
+    # Use old style quantization_method
+    new_quantization_methods = []
+    if quantization_method is not None:
+        # Convert quantization_method to list
+        if   isinstance(quantization_method, list):  pass
+        elif isinstance(quantization_method, str):   quantization_method = [ quantization_method, ]
+        elif isinstance(quantization_method, tuple): quantization_method = list(quantization_method)
+        else:
+            raise TypeError("Unsloth: quantization_method can only be a string or a list of strings")
+        pass
+        for i, quant_method in enumerate(quantization_method):
+            quant_method = quant_method.lower()
+            if   quant_method == "not_quantized":  quant_method = "f16"
+            elif quant_method == "fast_quantized": quant_method = "q8_0"
+            elif quant_method == "quantized":      quant_method = "q4_k_m"
+            elif quant_method is None:             quant_method = "q8_0"
+            new_quantization_methods.append(quant_method.lower())
+        pass
+    else:
+        new_quantization_methods.append(quantization_type.lower())
+    # Check if wrong method
+    for quant_method in new_quantization_methods:
+        if quant_method not in ALLOWED_QUANTS.keys():
+            error = f"Unsloth: Quant method = [{quant_method}] not supported. Choose from below:\n"
+            for key, value in ALLOWED_QUANTS.items():
+                error += f"[{key}] => {value}\n"
+            raise RuntimeError(error)
+        pass
+    pass

-        from huggingface_hub import HfApi
-        api = HfApi(token = token)
-        api.upload_folder(
-            folder_path = save_directory,
-            repo_id = repo_id,
-            repo_type = "model",
-            allow_patterns = ["*.gguf"],
+    # Go through all types and save individually - somewhat inefficient
+    # since we save F16 / BF16 multiple times
+    for quantization_type in new_quantization_methods:
+        metadata = _convert_to_gguf(
+            save_directory,
+            print_output = True,
+            quantization_type = quantization_type,
        )
+        if repo_id is not None:
+            prepare_saving(
+                model,
+                repo_id,
+                push_to_hub = True,
+                max_shard_size = "50GB",
+                private = True,
+                token = token,
+            )
+
+            from huggingface_hub import HfApi
+            api = HfApi(token = token)
+            api.upload_folder(
+                folder_path = save_directory,
+                repo_id = repo_id,
+                repo_type = "model",
+                allow_patterns = ["*.gguf"],
+            )
+        pass
    pass
    return metadata
 pass