Semantic Simulation — Gen 3: CfC/BAOAB, live gradients
Collection
Gen 3, CURRENT. The loss gradient reaches source tokens through Vφ, ξ and the exchange field; forward pass identical to Gen 2. • 9 items • Updated
Dimitar Gueorguiev
dimitarpg13
AI & ML interests
Transformers, Reinforcement Learning, Optimization, Causal Inference, Semantic Simulation
Recent Activity
updated a collection 2 days ago
Semantic Simulation — Gen 3: CfC/BAOAB, live gradients updated a model 2 days ago
dimitarpg13/semsimula-ladder-live-owt-d384-l2-attention-potential updated a model 2 days ago
dimitarpg13/semsimula-ladder-live-owt-d384-l2-noneOrganizations
None yet
updated a
collection 2 days ago
updated 4
models 2 days ago
dimitarpg13/semsimula-ladder-live-owt-d384-l2-attention-potential
Text Generation • Updated • 443
dimitarpg13/semsimula-ladder-live-owt-d384-l2-none
Text Generation • Updated • 528
dimitarpg13/semsimula-ladder-live-owt-d384-l4-none
Text Generation • Updated • 609
dimitarpg13/semsimula-ladder-live-owt-d384-l2-attention-potential-rfqk
Text Generation • Updated • 220
published a
model 2 days ago
updated 7
models 3 days ago
dimitarpg13/semsimula-ladder-owt-d384-l2-gpt2-matched
Text Generation • Updated • 892
dimitarpg13/semsimula-ladder-owt-d384-l2-attention-potential-rglive
Text Generation • Updated • 418
dimitarpg13/semsimula-ladder-owt-d384-l2-none-norc
Text Generation • Updated • 1.34k
dimitarpg13/semsimula-ladder-owt-d384-l2-none
Text Generation • Updated • 1.32k
dimitarpg13/semsimula-ladder-owt-d384-l2-attention-potential
Text Generation • Updated • 1.34k
dimitarpg13/semsimula-ladder-owt-d384-l2-attention
Text Generation • Updated • 1.3k
dimitarpg13/semsimula-ladder-live-owt-d384-l2-none-norc
Text Generation • Updated • 620
updated a
collection 3 days ago
published a
model 3 days ago
updated a
collection 4 days ago
published a
model 4 days ago
updated a
collection 5 days ago