Using LoRA, Full Finetune technique to finetune models in Qwen2.5-Coder series, improved score in several benchmarks (HumanEval, MBPP, DS1000, ...).
To Huy
tohuy2710
·
AI & ML interests
None yet
Organizations
None yet
models
10
tohuy2710/3b-1ep-ds-coder-v2
Updated
•
3
tohuy2710/3b-1ep-checkpoint
Updated
•
2
tohuy2710/Qwen2.5-Coder-1.5B-ds-coder-v2
Updated
•
2
tohuy2710/Qwen2.5-Coder-3B-Finetune-LeetcodeDataset
Updated
•
9
tohuy2710/5ep-checkpoint
Updated
•
2
tohuy2710/3ep-checkpoint
Updated
•
4
tohuy2710/checkpoint-dsc
Updated
•
4
tohuy2710/Qwen2.5-Coder-1.5B-Finetune-LeetcodeDataset
Updated
•
12
tohuy2710/qwen2.5-coder-1.5b-lora-r8-leetcodedataset
Updated
•
1
tohuy2710/Qwen2.5-Coder-0.5B-Finetune-LeetcodeDataset
Updated
•
10