Muche's picture

5 1

Muche

Truc95

·

AI & ML interests

None yet

Recent Activity

Reacted to merve's post with 😎 about 14 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

New activity in HuggingFaceTB/SmolVLM-Instruct 5 days ago

Best option for DocQVA->JSON

#11 opened 5 days ago by

New activity in HuggingFaceM4/Idefics3-8B-Llama3 20 days ago

Any Idea When This Will Be Supported in TGI?

#3 opened 4 months ago by

New activity in microsoft/Florence-2-large 5 months ago

Assert config.vision_config.model_type == 'davit', 'only DaViT is supported for now'

#44 opened 5 months ago by

New activity in microsoft/Phi-3-vision-128k-instruct 5 months ago

Will Phi-3 Vision receive the same re-training as Phi-3 Mini ?

#50 opened 5 months ago by

New activity in microsoft/Florence-2-large 5 months ago

How to increase max token output ?

#40 opened 5 months ago by