furyhawk 3c75694260 Add Unsloth notebook for fast finetuning with Llama and Qwen models ...

- Introduced a new Jupyter notebook `unsloth_nb.ipynb` for utilizing the Unsloth library.
- Implemented code to load and patch FastLanguageModel and FastQwen2Model for improved training speed.
- Configured models to support 4-bit quantization for reduced memory usage.
- Included detailed logging for model loading and system specifications.

2025-06-02 17:26:25 +08:00

..

format.sh

🔥 Remove isort configuration, since we use Ruff now (#1144)

2024-04-05 14:59:40 -05:00

lint.sh

🔥 Remove isort configuration, since we use Ruff now (#1144)

2024-04-05 14:59:40 -05:00

llamacpp.sh

Add Unsloth notebook for fast finetuning with Llama and Qwen models

2025-06-02 17:26:25 +08:00

prestart.sh

🔧 Use plain base official Python Docker image (#1351)

2024-09-22 18:25:29 +02:00

test.sh

♻️ Refactor user update (#689)

2024-03-12 17:29:49 +01:00

tests-start.sh

🚚 Move location of scripts to simplify file structure (#1352)

2024-09-22 18:19:57 +02:00