YuwonLee
2U1
AI & ML interests
Multi-modal LLMs
Recent Activity
new activity
3 days ago
google/gemma-3-4b-it:Finetuning script using HuggingFace
new activity
5 days ago
allenai/Molmo-7B-D-0924:Finetuning script for Molmo
new activity
18 days ago
DAMO-NLP-SG/VideoLLaMA3-2B-Image:Does the model cover videos?
Organizations
None yet
2U1's activity
Finetuning script using HuggingFace
#30 opened 3 days ago
by
2U1
Finetuning script for Molmo
2
#14 opened 6 months ago
by
2U1
Does the model cover videos?
#4 opened 18 days ago
by
2U1
Does this only supports image?
#6 opened 18 days ago
by
2U1
Multi image inference
1
#7 opened 24 days ago
by
2U1
Why is the weight separated?
3
#4 opened about 1 month ago
by
2U1
Finetuning scripts for Qwen2.5-VL (No llama-factory)
#11 opened about 2 months ago
by
2U1
[BUG] {'use_reentrant': True} results in "Gradients will be None"
2
#74 opened 2 months ago
by
RonanMcGovern

Is there a code for converting the model to onnx?
#7 opened about 2 months ago
by
2U1
Finetuning script using HuggingFace (No llama-factory)
36
#32 opened 7 months ago
by
2U1
RuntimeError: shape '[-1, 0]' is invalid for input of size 1206
3
#1 opened 3 months ago
by
2U1
Finetuning codes for SmolVLM
#25 opened 3 months ago
by
2U1
Finetuning script for Phi3.5-Vision
4
#24 opened 7 months ago
by
2U1
Fine tuning scripts for pixtral-12b
#33 opened 4 months ago
by
2U1
Fine-tuning
7
#10 opened 7 months ago
by
yukiarimo

Fine tuning scripts for pixtral -12b
#15 opened 4 months ago
by
2U1
Fine tuning scripts for pixtral-12b
#18 opened 4 months ago
by
2U1
force json output
1
#32 opened 5 months ago
by
joa23
Question about inputs in molmo
2
#13 opened 6 months ago
by
2U1
Finetuning scripts for Molmo
#5 opened 6 months ago
by
2U1