jkorstad/gemma-3-4B-it-thinking-function_calling-V0
Updated
Jonathan Korstad PRO
jkorstad
AI & ML interests
Deep Reinforcement Learning, Generative 3D, Accessibility, Multimodal Models, Agents, Computer Vision, XR. Staying curious.
Recent Activity
upvoted
an
article
3 days ago
Bringing Fusion Down to Earth: ML for Stellarator Optimization
updated
a collection
4 days ago
Science
Organizations
jkorstad/gemma-2-2B-it-thinking-function_calling-V0
Updated
jkorstad/multi-view-diffusion
Image-to-3D
•
Updated
•
2
jkorstad/wav2vec2-base-lang-id-finetuned-gtzan
Updated
jkorstad/distilhubert-finetuned-gtzan
Audio Classification
•
0.0B
•
Updated
•
15
jkorstad/distilhubert-finetuned-gtzan-finetuned-gtzan
Updated
jkorstad/InstantMesh
Image-to-3D
•
Updated
•
37
•
2
jkorstad/whisper-tiny
Updated
jkorstad/speecht5_tts_voxpopuli_jkorstad
Text-to-Audio
•
Updated
•
3
jkorstad/TTS
Updated
jkorstad/code-search-net-tokenizer
Updated
jkorstad/ML-Agents-SoccerTwos
Reinforcement Learning
•
Updated
•
15
jkorstad/poca-SoccerTwoss
Reinforcement Learning
•
Updated
•
21
jkorstad/rl_course_vizdoom_health_gathering_supreme
Reinforcement Learning
•
Updated
jkorstad/LunarLander-v2
Reinforcement Learning
•
Updated
jkorstad/ppo-LunarLander-v2
Updated
jkorstad/poca-SoccerTwos
Updated
jkorstad/a2c-PandaReachDense-v2
Reinforcement Learning
•
Updated
•
3
jkorstad/a2c-AntBulletEnv-v0
Reinforcement Learning
•
Updated
•
4
jkorstad/PyramidsRND
Reinforcement Learning
•
Updated
•
17
jkorstad/ppo-SnowballTarget
Reinforcement Learning
•
Updated
•
25
jkorstad/Reinforce-PixelCopter
Reinforcement Learning
•
Updated
jkorstad/CartPole-v2
Reinforcement Learning
•
Updated
jkorstad/Cartpole-v1
Reinforcement Learning
•
Updated
jkorstad/dqn-SpaceInvadersNoFrameskip-v4.2
Reinforcement Learning
•
Updated
•
6
jkorstad/dqn-SpaceInvadersNoFrameskip-v4.1
Reinforcement Learning
•
Updated
•
6
jkorstad/dqn-SpaceInvadersNoFrameskip-v4
Reinforcement Learning
•
Updated
•
24
jkorstad/Taxi-JPK-v3
Reinforcement Learning
•
Updated
jkorstad/q-FrozenLake-v1-4x4-noSlippery
Reinforcement Learning
•
Updated
jkorstad/Jk-LunarLander-v2
Reinforcement Learning
•
Updated
•
4
•
1