Metadata-Version: 2.4
Name: dqntrain
Version: 0.1.1
Summary: Headless, config-driven fine-tuning for LLMs on cloud GPUs
Author: dqntrain
License: MIT License
        
        Copyright (c) 2026 dqntrain
        
        Permission is hereby granted, free of charge, to any person obtaining a copy
        of this software and associated documentation files (the "Software"), to deal
        in the Software without restriction, including without limitation the rights
        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
        copies of the Software, and to permit persons to whom the Software is
        furnished to do so, subject to the following conditions:
        
        The above copyright notice and this permission notice shall be included in all
        copies or substantial portions of the Software.
        
        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
        SOFTWARE.
        
Project-URL: Homepage, https://github.com/dqntrain/dqntrain
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT 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: unsloth>=2025.1.0
Requires-Dist: trl>=0.15.0
Requires-Dist: transformers>=4.48.0
Requires-Dist: datasets>=3.0.0
Requires-Dist: accelerate>=1.0.0
Requires-Dist: peft>=0.14.0
Requires-Dist: bitsandbytes>=0.45.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: huggingface_hub>=0.27.0
Requires-Dist: matplotlib>=3.7.0
Dynamic: license-file


# dqntrain

Headless, config-driven fine-tuning for LLMs on cloud GPUs.

A programmatic fine-tuning toolkit inspired by Unsloth Studio's workflow, built for headless environments like **Kaggle**, **Google Colab**, and remote servers. No GUI required — just YAML/JSON recipes, clean Python APIs, and automatic GPU-aware defaults.

## Quick Start (Kaggle / Colab Notebook)

### 1. Install

```python
%%capture
!pip install dqntrain
```

### 2. Define a Config

```python
from dqntrain import auto_config_for_model

config = auto_config_for_model("unsloth/Qwen2.5-7B-Instruct-bnb-4bit")
config.training.num_train_epochs = 1
config.dataset.path = "yahma/alpaca-cleaned"
config.export.formats = ["lora", "gguf"]
```

### 3. Train

```python
from dqntrain import (
    ModelLoader, DatasetBuilder, DQNTrainer,
    TrainingMonitor, ModelExporter
)

loader = ModelLoader(config)
model, tokenizer = loader.load()
model = loader.apply_lora()

dataset = DatasetBuilder(config).build()

monitor = TrainingMonitor()
trainer = DQNTrainer(config, monitor=monitor)
trainer.create_trainer(model, tokenizer, dataset)
trainer.train()
monitor.plot()

ModelExporter(config).export(model, tokenizer)
```

That's it. The entire pipeline in ~15 lines.

## Features

| Capability | Description |
|---|---|
| **Model presets** | `auto_config_for_model()` detects your GPU and sets 4-bit, batch size, seq length |
| **LoRA / QLoRA** | `LoRAConfig` dataclass or YAML recipes |
| **Dataset formats** | JSON, JSONL, CSV, HuggingFace datasets, conversations — auto-detected |
| **Live monitoring** | Loss/LR/GPU tracking with matplotlib plots + JSONL logs |
| **Multi-format export** | LoRA, merged 16-bit, GGUF, Ollama Modelfile — in one call |
| **Headless-first** | No browser, no desktop UI — built for notebooks and servers |

## Project Structure

```
dqntrain/
├── dqntrain/
│   ├── config.py          # YAML/JSON recipes + auto GPU presets
│   ├── models.py          # Model loader + LoRA applier
│   ├── data.py            # Dataset builder (JSON/CSV/HF/conversations)
│   ├── trainer.py         # SFTTrainer wrapper with cloud paths
│   ├── observability.py   # Live metrics, plots, JSONL logging
│   ├── export.py          # GGUF, merged, Ollama, Hub push
│   └── utils.py           # Environment detection + GPU info
├── configs/
│   ├── quick_lora.yaml    # T4-optimized 4-bit recipe
│   └── full_finetune.yaml # P100+ 16-bit recipe
└── notebooks/
    └── kaggle_template.ipynb  # Ready-to-run Kaggle notebook
```

## Config Recipes

Save a YAML file and pass it to `load_config()`:

```yaml
model:
  name: "unsloth/Qwen2.5-7B-Instruct-bnb-4bit"
  max_seq_length: 2048
  load_in_4bit: true

lora:
  r: 16
  lora_alpha: 32
  target_modules: [q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj]

training:
  num_train_epochs: 1
  per_device_train_batch_size: 1
  gradient_accumulation_steps: 4
  learning_rate: 2.0e-4
  output_dir: "./outputs"

dataset:
  path: "yahma/alpaca-cleaned"
  instruction_column: "instruction"
  response_column: "output"

export:
  formats: [lora, gguf]
  quantization: "q4_k_m"
```

## Supported Dataset Formats

`DatasetBuilder` auto-detects:

- **HuggingFace datasets** (`dataset.path = "yahma/alpaca-cleaned"`)
- **JSON / JSONL** files with `instruction`/`response` or `conversations` arrays
- **CSV** files with text columns
- **In-memory lists** of dicts

## GPU-Aware Defaults

`auto_config_for_model()` inspects your GPU and adjusts:

- `load_in_4bit` — forced on for T4 (15 GB), optional on P100/V100
- `per_device_train_batch_size` — smaller for big models
- `max_seq_length` — capped to fit VRAM
- `gradient_accumulation_steps` — scaled up to maintain effective batch size

## Export Formats

`ModelExporter` can produce any combination of:

- `lora` — LoRA adapter (smallest, fastest to save)
- `merged` / `safetensors` — Full 16-bit merged model
- `gguf` — Quantized GGUF for llama.cpp / Ollama
- `ollama` — `Modelfile` ready for `ollama create`

## CLI Usage

```bash
# Install deps
pip install dqntrain

# Run from a config file
dqntrain --config configs/quick_lora.yaml

# Override model and dataset
dqntrain --model unsloth/Phi-4 --dataset my_data.jsonl --epochs 2
```

## Kaggle-Specific Tips

1. **Enable Internet** in notebook settings for `pip install` and HF downloads.
2. **Persist outputs** — everything in `/kaggle/working` survives the session.
3. **Save Versions** — click "Save Version" → "Run" to execute headlessly. Logs still write to `/kaggle/working`.
4. **Dataset inputs** — upload custom JSON/CSV via Kaggle Datasets, then reference them with `config.dataset.path = "/kaggle/input/your-dataset/file.json"`.

## License

MIT. This package depends on Unsloth (Apache 2.0 core), TRL, and Transformers.
