MLX
English
math
"batch_size": 1,
"fine_tune_type": "lora",
"grad_checkpoint": true,
"iters": 1000,
"learning_rate": 2e-05,
"lora_parameters": {
    "rank": 8,
    "dropout": 0.0,
    "scale": 20.0
"test_loss": 1.017, 
"Test ppl": 2.764
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mlx-community/Qwen3-0.6B

Finetuned
Qwen/Qwen3-0.6B
Finetuned
(174)
this model

Dataset used to train mlx-community/Qwen3-0.6B