Muche

Truc95

AI & ML interests

None yet

Recent Activity

Reacted to merve's post with 😎 about 18 hours ago

small but mighty 🔥 you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨ I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb

New activity 5 days ago

HuggingFaceTB/SmolVLM-Instruct:Best option for DocQVA->JSON

New activity 20 days ago

HuggingFaceM4/Idefics3-8B-Llama3:Any Idea When This Will Be Supported in TGI?

View all activity

Organizations

None yet

Truc95's activity

reacted to merve's post with 😎 about 18 hours ago

Post

1471

small but mighty 🔥
you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨
I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb