tohuy2710
/

Qwen2.5-Coder-0.5B-Finetune-LeetcodeDataset

Model card Files Files and versions

Qwen/Qwen2.5-Coder-0.5B finetuned 3 epochs on LeetCodeDataset
Pass@1 on humaneval has improved from 0.28 to 0.31

Downloads last month: 5

Safetensors

Model size

0.5B params

Tensor type

F32

·

Inference Providers NEW

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

Model tree for tohuy2710/Qwen2.5-Coder-0.5B-Finetune-LeetcodeDataset

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-Coder-0.5B

Finetuned

(20)

this model

Finetunes

1 model

Dataset used to train tohuy2710/Qwen2.5-Coder-0.5B-Finetune-LeetcodeDataset

Collection including tohuy2710/Qwen2.5-Coder-0.5B-Finetune-LeetcodeDataset

Qwen2.5-Coder Finetune LeetCodeDataset

Using LoRA, Full Finetune technique to finetune models in Qwen2.5-Coder series, improved score in several benchmarks (HumanEval, MBPP, DS1000, ...). • 4 items • Updated 15 days ago