qwen3-1.7b-docs-nextjs-20260601-0306/README.md

license, language, library_name, pipeline_tag, base_model, base_model_relation, datasets, tags

license	language	library_name	pipeline_tag	base_model	base_model_relation	datasets	tags
apache-2.0	en	mlx	text-generation	Qwen/Qwen3-1.7B	finetune	jokernifty/docs-instruct-nextjs-20260601-0306	mlx qwen2 instruction-tuning downftuner synthetic-data

qwen3-1.7b-docs-20260601-0306

LoRA fine-tune of Qwen/Qwen3-1.7B on a freshly-synthesized mixed-Wikipedia instruction dataset.

• Training: MLX-LM LoRA, 800 iterations, 16 layers, LR 1.0e-5.
• Dataset: jokernifty/docs-instruct-nextjs-20260601-0306
• Pipeline: DownFTuner

Usage

from mlx_lm import load, generate
model, tokenizer = load("jokernifty/qwen3-1.7b-docs-nextjs-20260601-0306")
print(generate(model, tokenizer, prompt="Explain the Krebs cycle.", max_tokens=200))

For transformers, convert from MLX format with mlx_lm.convert --hf-path jokernifty/qwen3-1.7b-docs-nextjs-20260601-0306 or load via mlx_lm.