thkim0305/llama3.2_1B_vl
Image-Text-to-Text • 2B • Updated • 271
LLaVA-variable_sizes
collection of self-trained LLaVA (MLLM) models following the LLaVA-v1.5 tuning methods using diverse LLM families with different sizes
-
-
thkim0305/llama3.2_3B_vl
Image-Text-to-Text • 4B • Updated • 229 -
thkim0305/qwen2.5_0.5B_vl
Image-Text-to-Text • 0.8B • Updated • 170 -
thkim0305/llama3.1_8B_vl
Image-Text-to-Text • 8B • Updated • 1 -
thkim0305/qwen2.5_3B_vl
Image-Text-to-Text • 3B • Updated • 1 -
thkim0305/qwen2.5_1.5B_vl
Image-Text-to-Text • 2B • Updated • 2