Huynh Tien Dat
noflash41
ยท
AI & ML interests
Finetune LLM, Diffusion model, Multi-modal
Recent Activity
upvoted an article 3 days ago
Llasa Goes RL: Training LLaSA with GRPO for Improved Prosody and Expressiveness liked a dataset 26 days ago
TIGER-Lab/MMLU-Pro updated a model 3 months ago
noflash41/unsloth_qwen3_4b_instruct_2507_1ae22f21_finetuneOrganizations
None yet