production checkpoint
Generate with Phase 1 Weights
Loading pretrained checkpoint status.
Kyberne Lab / EventMix
Sparse Event Transition Language Model
Generate with the deeper pretrained membrane-free model whose only sequence state is a fixed event transition matrix.
0 attention layers
12 repeated event mixers
12.5% exact event rate
fixed transition state
loaded model
96x3 / Context 64
- Checkpoint
- step 4,750
- Validation loss
- 7.258231
- Validation accuracy
- 9.96%
- Event rate
- 0.14816
- Optimizer state
- No
- Online updates
- No
GPT-2 BPE Local Attention Spiking Memory SwiGLU Token Readout
model output
Completion
The future of learning is ready for generation.
token distribution
Top Candidates
No token distribution available.
live state
Runtime Signals
- Prompt tokens
- -
- Spike rate
- -
- Attention gate
- -
- State memory
- -
- Plastic connections
- 8,192
- Device
- CPU
benchmark controls
Run EVM-2 v0.25
Ready. Run the EVM-2 v0.25 checkpoint benchmark.
checkpoint and reference
MNIST 32x32 Spiking LeNet Path
Dataset
The verified checkpoint uses MNIST IDX handwritten digits only. Each 28x28 digit is normalized into a 32x32 retina input; no alphabet or symbol dataset is used offline.
Online scope
The lab keeps the MNIST-trained visual hierarchy fixed enough for comparison, while the interactive adapter can absorb user-drawn letters and symbols as online learning samples.
Generalization test
The same sparse visual evidence is projected into an 8x12 ASCII matrix output. New classes are learned incrementally, making the page a direct test of post-training generalization.
pretrained model
evm-2-v0.25-mnist-92p0
- Protocol
- evm-2-mnist-spiking-lenet-v1
- Architecture
- Retina -> S1 -> C1 -> C2 -> Detector -> Part -> Centroid
- Small validation
- 277 / 300, 92.3%
- Large validation
- 920 / 1000, 92.0%
interactive adapter
Online ASCII Test / Train
Draw a digit, letter, or symbol, then test or train it online.
latest result
92.3%
- Correct
- 277 / 300
- Elapsed
- -
- Composable part memory
- 100.0%
- Active assembly rate
- 25.4%
- ASCII matrix readout
- top-2 blend 0.5
- Protocol
- evm-2-mnist-spiking-lenet-v1
network path
Retina -> S1/C1/C2 -> Part Memory -> Centroid
Retina 1024 S1 12 maps C1 3072 C2 768 Detector 64 Part 96 Centroid 320 Output 8x12
confusion matrix
Actual vs Predicted
actual architecture
EVM-2 Runtime Forward Graph
retina / feature maps descriptor prototype banks centroid readout
token corpus
Train Sentence Next-Token Memory
Ready. Train GEMN2 token SNN on sentence continuations.
latest GEMN2 metrics
-
- Top-1
- -
- Top-5
- -
- Candidate recall
- -
- Avg candidates
- -
- Vocabulary
- -
- Trained tokens
- -
evaluation
Test Sentence Prediction
Step 1 Pick a corpus
Step 2 Train token SNN
Step 3 Test next token
Step 4 Predict top-k
No test run yet.
next-token prediction
Input Sentence, Predict Next Token
No prediction yet.
session controls
Reset or Run Token Benchmark
token benchmark
Before / Train / After
- Protocol
- gemn2-token-snn-v0
- Train top-5
- -
- After top-1
- -
- Prediction
- -
actual architecture
GEMN2 Token SNN Runtime Graph
BPE token / embedding spikes stateful SNN traces candidate next-token decoder
self-supervised predictive event model
12-Head Predictive Recurrent Generation
Connecting to the pretrained EventMix service.
generated text
Autoregressive Output
No generation yet.
next-token distribution
-
runtime state
event-transition-service-v1
- Prompt tokens
- -
- Generated tokens
- -
- Event rate
- -
- Matched order
- -
- Cached state
- -
- Elapsed
- -
experimental checkpoint
Local Learning. No Membrane Potential.
- Tokenizer
- -
- Trainable params
- -
- Model buffers
- -
- Trained tokens
- -
- Train steps
- -
- Best step
- -
- Validation loss
- -
- Validation PPL
- -
- Test PPL
- -
- Memory contribution
- -
- Story repetition
- -
- Micro reasoning
- -
parallel predictive memory
Recurrent Event Banks x 6
Byte BPE1,024 symbols
Current Eventsigned 12.5%
INT8 Statesix parallel timescales
Event Memorylocal INT4 updates
Context Rerankeight candidates
- Model dim
- 672
- Layers
- 6
- Heads
- 12
- Events / head
- 7