Lion Optimized

AXL-TestGen-Lion

Test generation. 15.2M params. PPL 1.15. Context 2048 bytes.

15M
Parameters
1.15
Perplexity
10 min
Training
31 MB
GGUF
PropertyValue
ArchitectureMulti-Scale Transformer
d_model?
Attention Heads?
Layers per Scale?
Context Window2048 bytes
Downsample Factors[1, 2, 4]
Vocab Size258 (byte-level)
OptimizerLion
Trained on 10MB function-to-test pairs. 163 steps in 10 min.
MetricValue
Final Loss0.1433
Perplexity1.15
Training Steps163
Training Time10 min

Usage

ollama create axl-testgen-lion -f Modelfile
ollama run axl-testgen-lion "def fibonacci():"
Generates unit tests from function signatures.
FileSizeFormat
F16 GGUF31 MBFull precision
Q4_K_M GGUF18 MB4-bit quantized
GGUF files work with Ollama and llama.cpp. Q4_K_M is about 3x smaller than F16.
← All AXL Models