P4o1o
/

Qwen3_0.6-NvidiaOpenCodeReasoning

code-generation

Model card Files Files and versions

P4o1o/Qwen3_0.6-NvidiaOpenCodeReasoning

Fine-tuned version of Qwen/Qwen3-0.6B on NVIDIA's OpenCodeReasoning dataset

Training Hyperparameters

Batch size: 16
Learning rate: 1e-05
Epochs: 3
Max length: 2048

Downloads last month: 41

Safetensors

Model size

752M params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for P4o1o/Qwen3_0.6-NvidiaOpenCodeReasoning

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(223)

this model

Dataset used to train P4o1o/Qwen3_0.6-NvidiaOpenCodeReasoning