unsloth-mlx 0.3.3__tar.gz

unsloth_mlx-0.3.3/LICENSE

@@ -0,0 +1,190 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to the Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright [2026-] Abdur Rahim
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

unsloth_mlx-0.3.3/PKG-INFO

@@ -0,0 +1,279 @@
+Metadata-Version: 2.4
+Name: unsloth-mlx
+Version: 0.3.3
+Summary: MLX-powered LLM fine-tuning for Apple Silicon - A drop-in replacement for Unsloth
+Author: Unsloth-MLX Contributors
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/ARahim3/unsloth-mlx
+Project-URL: Documentation, https://github.com/ARahim3/unsloth-mlx#readme
+Project-URL: Repository, https://github.com/ARahim3/unsloth-mlx
+Project-URL: Issues, https://github.com/ARahim3/unsloth-mlx/issues
+Keywords: llm,fine-tuning,mlx,apple-silicon,lora,unsloth,mac
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: mlx>=0.20.0
+Requires-Dist: mlx-lm>=0.18.0
+Requires-Dist: transformers>=4.36.0
+Requires-Dist: tokenizers>=0.15.0
+Requires-Dist: datasets>=2.14.0
+Requires-Dist: huggingface-hub>=0.20.0
+Requires-Dist: numpy>=1.23.0
+Requires-Dist: tqdm>=4.65.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: black>=23.7.0; extra == "dev"
+Requires-Dist: ruff>=0.0.284; extra == "dev"
+Requires-Dist: ipython>=8.12.0; extra == "dev"
+Provides-Extra: vlm
+Requires-Dist: mlx-vlm>=0.1.0; extra == "vlm"
+Provides-Extra: train
+Requires-Dist: trl>=0.7.0; extra == "train"
+Requires-Dist: peft>=0.7.0; extra == "train"
+Requires-Dist: wandb>=0.15.0; extra == "train"
+Provides-Extra: all
+Requires-Dist: unsloth-mlx[dev,train,vlm]; extra == "all"
+Dynamic: license-file
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/ARahim3/unsloth-mlx/main/unsloth_mlx_logo_f.png" alt="Unsloth-MLX Logo" width="200"/>
+</p>
+<h1 align="center">Unsloth-MLX</h1>
+
+<p align="center">
+  <strong>Fine-tune LLMs on your Mac with Apple Silicon</strong><br>
+  <em>Prototype locally, scale to cloud. Same code, just change the import.</em>
+</p>
+
+<p align="center">
+  <a href="#installation"><img src="https://img.shields.io/badge/Platform-Apple%20Silicon-black?logo=apple" alt="Platform"></a>
+  <a href="#requirements"><img src="https://img.shields.io/badge/Python-3.9+-blue?logo=python&logoColor=white" alt="Python"></a>
+  <a href="https://github.com/ml-explore/mlx"><img src="https://img.shields.io/badge/MLX-0.20+-green" alt="MLX"></a>
+  <a href="#license"><img src="https://img.shields.io/badge/License-Apache%202.0-orange" alt="License"></a>
+</p>
+
+<p align="center">
+  <a href="#quick-start">Quick Start</a> ·
+  <a href="#supported-training-methods">Training Methods</a> ·
+  <a href="#examples">Examples</a> ·
+  <a href="#project-status">Status</a>
+</p>
+
+---
+
+> [!NOTE]
+> **Why I Built This (A Personal Note)**
+>
+> I rely on Unsloth for my daily fine-tuning on cloud GPUs—it's the gold standard for me. But recently, I started working on a MacBook M4 and hit a friction point: I wanted to prototype locally on my Mac, then scale up to the cloud without rewriting my entire training script.
+>
+> Since Unsloth relies on Triton (which Macs don't have, yet), I couldn't use it locally. I built `unsloth-mlx` to solve this specific "Context Switch" problem. It wraps Apple's native MLX framework in an Unsloth-compatible API.
+>
+> **The goal isn't to replace Unsloth or claim superior performance.** The goal is **code portability**: allowing you to write `FastLanguageModel` code once on your Mac, test it, and then push that *exact same script* to a CUDA cluster. It solves a workflow problem, not just a hardware one.
+>
+> This is an "unofficial" project built by a fan, for fans who happen to use Macs. It's helping me personally, and if it helps others like me, then I'll have my satisfaction.
+
+## Why Unsloth-MLX?
+
+Bringing the [Unsloth](https://github.com/unslothai/unsloth) experience to Mac users via Apple's [MLX](https://github.com/ml-explore/mlx) framework.
+
+- 🚀 **Fine-tune LLMs locally** on your Mac (M1/M2/M3/M4/M5)
+- 💾 **Leverage unified memory** (up to 512GB on Mac Studio)
+- 🔄 **Same API as Unsloth** - your existing code just works!
+- 📦 **Export anywhere** - HuggingFace format, GGUF for Ollama/llama.cpp
+
+```python
+# Unsloth (CUDA)                        # Unsloth-MLX (Apple Silicon)
+from unsloth import FastLanguageModel   from unsloth_mlx import FastLanguageModel
+from trl import SFTTrainer              from unsloth_mlx import SFTTrainer
+
+# Rest of your code stays exactly the same!
+```
+
+## What This Is (and Isn't)
+
+**This is NOT** a replacement for Unsloth or an attempt to compete with it. Unsloth is incredible - it's the gold standard for efficient LLM fine-tuning on CUDA.
+
+**This IS** a bridge for Mac users who want to:
+- 🧪 **Prototype locally** - Experiment with fine-tuning before committing to cloud GPU costs
+- 📚 **Learn & iterate** - Develop your training pipeline with fast local feedback loops
+- 🔄 **Then scale up** - Move to cloud NVIDIA GPUs + original Unsloth for production training
+
+```
+Local Mac (Unsloth-MLX)     →     Cloud GPU (Unsloth)
+   Prototype & experiment          Full-scale training
+   Small datasets                  Large datasets
+   Quick iterations                Production runs
+```
+
+## Project Status
+
+> 🚀 **v0.3.2** - Full dataset handling + multi-turn conversations!
+
+| Feature | Status | Notes |
+|---------|--------|-------|
+| SFT Training | ✅ Stable | Native MLX training |
+| Model Loading | ✅ Stable | Any HuggingFace model |
+| Save/Export | ✅ Stable | HF format, GGUF |
+| DPO Training | ✅ Stable | **Full DPO loss** |
+| ORPO Training | ✅ Stable | **Full ORPO loss** |
+| GRPO Training | ✅ Stable | **Multi-generation + reward** |
+| KTO/SimPO | ✅ Stable | Proper loss implementations |
+| Chat Templates | ✅ Stable | 15 models (llama, gemma, qwen, phi, mistral) |
+| Response-Only Training | ✅ Stable | `train_on_responses_only()` |
+| **Multi-turn Merging** | ✅ **NEW** | `to_sharegpt()` + `conversation_extension` |
+| **Column Mapping** | ✅ **NEW** | `apply_column_mapping()` auto-rename |
+| **Dataset Config** | ✅ **NEW** | `HFDatasetConfig` structured loading |
+| Vision Models | ⚠️ Beta | Via mlx-vlm |
+| PyPI Package | ✅ Available | `uv pip install unsloth-mlx` |
+
+## Installation
+
+```bash
+# Using uv (recommended - faster and more reliable)
+uv pip install unsloth-mlx
+
+# Or using pip
+pip install unsloth-mlx
+
+# From source (for development)
+git clone https://github.com/ARahim3/unsloth-mlx.git
+cd unsloth-mlx
+uv pip install -e .
+```
+
+## Quick Start
+
+```python
+from unsloth_mlx import FastLanguageModel, SFTTrainer, SFTConfig
+from datasets import load_dataset
+
+# Load any HuggingFace model (1B model for quick start)
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="mlx-community/Llama-3.2-1B-Instruct-4bit",
+    max_seq_length=2048,
+    load_in_4bit=True,
+)
+
+# Add LoRA adapters
+model = FastLanguageModel.get_peft_model(
+    model,
+    r=16,
+    target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
+    lora_alpha=16,
+)
+
+# Load a dataset (or create your own)
+dataset = load_dataset("yahma/alpaca-cleaned", split="train[:100]")
+
+# Train with SFTTrainer (same API as TRL!)
+trainer = SFTTrainer(
+    model=model,
+    train_dataset=dataset,
+    tokenizer=tokenizer,
+    args=SFTConfig(
+        output_dir="outputs",
+        per_device_train_batch_size=2,
+        learning_rate=2e-4,
+        max_steps=50,
+    ),
+)
+trainer.train()
+
+# Save (same API as Unsloth!)
+model.save_pretrained("lora_model")  # Adapters only
+model.save_pretrained_merged("merged", tokenizer)  # Full model
+model.save_pretrained_gguf("model", tokenizer, quantization_method="q4_k_m")  # GGUF
+```
+
+### Chat Templates & Response-Only Training
+
+```python
+from unsloth_mlx import get_chat_template, train_on_responses_only
+
+# Apply chat template (supports llama-3, gemma, qwen, phi, mistral, etc.)
+tokenizer = get_chat_template(tokenizer, chat_template="llama-3")
+
+# Or auto-detect from model name
+tokenizer = get_chat_template(tokenizer, chat_template="auto")
+
+# Train only on responses (not prompts) - more efficient!
+trainer = train_on_responses_only(
+    trainer,
+    instruction_part="<|start_header_id|>user<|end_header_id|>\n\n",
+    response_part="<|start_header_id|>assistant<|end_header_id|>\n\n",
+)
+```
+
+## Supported Training Methods
+
+| Method | Trainer | Implementation | Use Case |
+|--------|---------|----------------|----------|
+| **SFT** | `SFTTrainer` | ✅ Native MLX | Instruction fine-tuning |
+| **DPO** | `DPOTrainer` | ✅ Native MLX | Preference learning (proper log-prob loss) |
+| **ORPO** | `ORPOTrainer` | ✅ Native MLX | Combined SFT + odds ratio preference |
+| **GRPO** | `GRPOTrainer` | ✅ Native MLX | Reasoning with multi-generation (DeepSeek R1 style) |
+| **KTO** | `KTOTrainer` | ✅ Native MLX | Kahneman-Tversky optimization |
+| **SimPO** | `SimPOTrainer` | ✅ Native MLX | Simple preference optimization |
+| **VLM** | `VLMSFTTrainer` | ⚠️ Beta | Vision-Language models |
+
+## Examples
+
+Check [`examples/`](examples/) for working code:
+- Basic model loading and inference
+- Complete SFT fine-tuning pipeline
+- RL training methods (DPO, GRPO, ORPO)
+
+## Requirements
+
+- **Hardware**: Apple Silicon Mac (M1/M2/M3/M4/M5)
+- **OS**: macOS 13.0+ (15.0+ recommended for large models)
+- **Memory**: 16GB+ unified RAM (32GB+ for 7B+ models)
+- **Python**: 3.9+
+
+## Comparison with Unsloth
+
+| Feature | Unsloth (CUDA) | Unsloth-MLX |
+|---------|----------------|-------------|
+| Platform | NVIDIA GPUs | Apple Silicon |
+| Backend | Triton Kernels | MLX Framework |
+| Memory | VRAM (limited) | Unified (up to 512GB) |
+| API | Original | 100% Compatible |
+| Best For | Production training | Local dev, large models |
+
+## Contributing
+
+Contributions welcome! Areas that need help:
+- Custom MLX kernels for even faster training
+- More comprehensive test coverage
+- Documentation and examples
+- Testing on different M-series chips (M1, M2, M3, M4, M5)
+- VLM training improvements
+
+## License
+
+Apache 2.0 - See [LICENSE](LICENSE) file.
+
+## Acknowledgments
+
+- [Unsloth](https://github.com/unslothai/unsloth) - The original, incredible CUDA library
+- [MLX](https://github.com/ml-explore/mlx) - Apple's ML framework
+- [MLX-LM](https://github.com/ml-explore/mlx-lm) - LLM utilities for MLX
+- [MLX-VLM](https://github.com/Blaizzy/mlx-vlm) - Vision model support
+
+---
+
+<p align="center">
+  <strong>Community project, not affiliated with Unsloth AI or Apple.</strong><br>
+  ⭐ Star this repo if you find it useful!
+</p>