Shyam Sudhakaran
shyamsn97
AI & ML interests
Reinforcement Learning, Open-Ended Algorithms, Neural Cellular Automata
Recent Activity
updated a model 6 days ago
shyamsn97/tinkerbell-chat-sft liked a dataset 6 days ago
blanchon/opencs2_dataset upvoted a paper about 2 months ago
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent SkillsOrganizations
models 23
shyamsn97/tinkerbell-chat-sft
Updated
shyamsn97/tinkerbell-chat-sft-local
Updated
shyamsn97/table-cube-regen-damage-detection-20
Updated • 4
shyamsn97/cube-regen-damage-detection
Updated • 2
shyamsn97/Mario-GPT2-700-context-length
Text Generation • Updated • 1.44k • 13
shyamsn97/pretrained-mario-gpt-700ctx-bart-text-encoder-new-elevation-v2
Text Generation • Updated • 7
shyamsn97/pretrained-mario-gpt-700ctx-bart-text-encoder-v2-editing
Text Generation • Updated • 11
shyamsn97/pretrained-mario-gpt-700ctx-bart-text-encoder-v2
Text Generation • Updated • 5
shyamsn97/from-scratch-mario-gpt-700ctx-bart-text-encoder
Text Generation • Updated • 8
shyamsn97/MarioBert-448-inpaint-context-length
Fill-Mask • Updated • 6