aidystark/function
Text Generation • 0.3B • Updated • 47
Aidy Osu
aidystark
AI & ML interests
Vision;Language;Speech
Recent Activity
updated a model about 20 hours ago
aidystark/function published a model about 20 hours ago
aidystark/functionOrganizations
updated a
model about 20 hours ago
published a
model about 20 hours ago
AttributeError: 'Gemma3Config' object has no attribute 'num_hidden_layers'
🔥 2
1
#1 opened 6 months ago
by aidystark
liked 2
models 6 months ago
upvoted an article 7 months ago
Article
mmBERT: ModernBERT goes Multilingual
- +4
•
140
liked a
model 7 months ago
reactedto chansung's post with 👍 9 months ago
Post
4707
YAML engineering becomes more and more important than ever from infra provisioning to model training (recipes).
Here, I built a simple editor first for @dstackai , and I will share the live endpoint this week. Let me know what you think about this approach.
Based on this approach, if people think this is useful, I am going to do the same thing for the LLM training recipes for popular frameworks such as Hugging Face open-r1, Axolotl, and so on. Let me hear.
Here, I built a simple editor first for @dstackai , and I will share the live endpoint this week. Let me know what you think about this approach.
Based on this approach, if people think this is useful, I am going to do the same thing for the LLM training recipes for popular frameworks such as Hugging Face open-r1, Axolotl, and so on. Let me hear.
upvoted a collection about 1 year ago
liked 2
models about 1 year ago
commented a
paper about 1 year ago
liked a
Space about 1 year ago
commented a
paper about 1 year ago
liked a
model about 1 year ago
liked 2
Spaces over 1 year ago
liked 2
models over 1 year ago
reactedto merve's post with 🚀 over 1 year ago
Post
2704
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
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