tohuy2710
/

Qwen2.5-Coder-1.5B-Finetune-LeetcodeDataset

Model card Files Files and versions

Qwen/Qwen2.5-Coder-1.5B trained 5 epochs on newfade/LeetCodeDataset
HumanEval improved from 0.439 to 0.5
DS1000 pass@1 improved from 0.255 (Base Model) to 0.274
Other benchmarks' result will update as soon as possible!

Downloads last month: 16

Inference Providers NEW

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

Model tree for tohuy2710/Qwen2.5-Coder-1.5B-Finetune-LeetcodeDataset

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

(30)

this model

Dataset used to train tohuy2710/Qwen2.5-Coder-1.5B-Finetune-LeetcodeDataset

Collection including tohuy2710/Qwen2.5-Coder-1.5B-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 Oct 12