Michael Ha's picture

1 8

Michael Ha

mlxha

·

mlxha

AI & ML interests

None yet

Recent Activity

updated a model about 2 months ago

mlxha/Qwen2.5-7B-Instruct-grpo-medmcqa-medi70

published a model about 2 months ago

mlxha/Qwen2.5-7B-Instruct-grpo-medmcqa-medi70

updated a model 2 months ago

mlxha/Llama-3.1-8B-Instruct-GRPO-medmcqa

View all activity

Organizations

mlxha 's models 34

mlxha/Qwen2.5-7B-Instruct-grpo-medmcqa-medi70

Text Generation • 8B • Updated Jul 9 • 8

mlxha/Llama-3.1-8B-Instruct-GRPO-medmcqa

Text Generation • 8B • Updated Jul 2 • 6

mlxha/llama8b-sft-grpo-medmcqa

Text Generation • 8B • Updated Jul 1 • 8

mlxha/medicouenne7b-grpo-medmcqa

Text Generation • 8B • Updated Jul 1 • 8

mlxha/Qwen3-8B-grpo-medmcqa-medi70

Text Generation • 8B • Updated May 27 • 265

mlxha/Qwen3-8B-grpo-medmcqa-v2

Text Generation • 8B • Updated May 19 • 12 • 1

mlxha/Qwen3-32B-grpo-medmcqa

Updated May 13 • 1

mlxha/Qwen3-4B-grpo-medmcqa

Text Generation • 4B • Updated May 12 • 31.1k • 1

mlxha/Qwen3-8B-grpo-medmcqa

Text Generation • 8B • Updated May 11 • 9 • 2

mlxha/DeepSeek-R1-Distill-Llama-8B-GRPO-medmcqa-notemplate

8B • Updated May 6 • 6

mlxha/Qwen-2.5-3B-grpo-medmcqa

Text Generation • 3B • Updated Apr 18 • 10

mlxha/Qwen-2.5-3B-grpo-code

Text Generation • 3B • Updated Apr 18 • 9

mlxha/DeepSeek-R1-Distill-Llama-8B-GRPO-code-2

8B • Updated Apr 17 • 4

mlxha/DeepSeek-R1-Distill-Llama-8B-GRPO-code

8B • Updated Apr 15 • 4

mlxha/DeepSeek-R1-Distill-Llama-8B-notemplate

Text Generation • 8B • Updated Apr 14 • 6

mlxha/DeepSeek-R1-Distill-Llama-8B-GRPO-medmcqa

Text Generation • 8B • Updated Mar 24 • 3

mlxha/Qwen2.5-1.5B-Open-R1-Code-GRPO

2B • Updated Mar 13 • 3

mlxha/Qwen-2.5-7B-GRPO-test2

mlxha/Qwen-2.5-7B-GRPO-test

Text Generation • 8B • Updated Mar 11 • 3

mlxha/Qwen-2.5-7B-Simple-RL

mlxha/Qwen2.5-1.5B-Open-R1-Distill

mlxha/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

mlxha/mnlp-openaint-phi3-mini-mcq-dpo-sft-dpo-final

Text Generation • 4B • Updated Jun 13, 2024 • 2

mlxha/mnlp-openaint-phi3-mini-mcq-dpo-final-v2

Text Generation • 4B • Updated Jun 13, 2024 • 2

mlxha/mnlp-openaint-phi3-mini-mcq-dpo-sft-final-v2

Text Generation • 4B • Updated Jun 13, 2024 • 2

mlxha/mnlp-openaint-phi3-mini-mcq-dpo-final

Text Generation • 4B • Updated Jun 13, 2024 • 4

mlxha/mnlp-openaint-phi3-mini-mcq-dpo-sft-final

Text Generation • 4B • Updated Jun 13, 2024 • 2

mlxha/mnlp-openaint-phi3-mini-mcq-dpo-v2

Text Generation • 4B • Updated Jun 12, 2024 • 2

mlxha/mnlp-openaint-phi3-mini-mcq-dpo-sft-mmlu

Text Generation • 4B • Updated Jun 11, 2024 • 2

mlxha/mnlp-openaint-phi3-mini-mcq-dpo-sft

Text Generation • 4B • Updated Jun 10, 2024 • 4