collection of self-trained LLaVA (MLLM) models following the LLaVA-v1.5 tuning methods using diverse LLM families with different sizes
TAEHEON KIM
thkim0305
AI & ML interests
generative models
Recent Activity
upvoted a paper 7 days ago
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts liked a dataset 5 months ago
SNUMPR/DRAKE updated a collection 5 months ago
LLaVA-variable_sizesOrganizations
None yet
models 42
thkim0305/llama3.2_3B_vl_1_4
Updated
thkim0305/new_drake_baselines
Updated
thkim0305/llama3.2_3B_vl_internvl
Image-Text-to-Text • 4B • Updated • 6
thkim0305/new_llm_baselines
Updated
thkim0305/evolving_weights
Updated
thkim0305/llama3.2_3B_vl_kl
Image-Text-to-Text • 4B • Updated • 9
thkim0305/llama3.2_1B_vl_pretrain
Image-Text-to-Text • 2B • Updated • 3
thkim0305/llama3.2_3B_vl_pretrain
Image-Text-to-Text • 4B • Updated • 4
thkim0305/new_hflb_baselines
Updated
thkim0305/drake_baselines
Updated
datasets 0
None public yet