Remek/basal-1.0-4.5B
Text Generation • 5B • Updated • 1.81k • 7
basal-1.0
Calibrated typed-decision models for Polish (and English): one forward pass, probabilities over the allowed answers. Engine: github.com/rkinas/basal
Note Main model, bf16, with early-exit heads
Remek/basal-1.0-1.5B
Text Generation • 2B • Updated • 1.01k • 2Note Lite model: 2.5x throughput
Remek/basal-1.0-4.5B-FP8
Text Generation • 5B • Updated • 46 • 1Note ModelOpt FP8 for vLLM
Remek/basal-1.0-4.5B-NVFP4
Text Generation • 2B • Updated • 239Note ModelOpt NVFP4 for vLLM (Blackwell, throughput)
Remek/basal-1.0-1.5B-FP8
Text Generation • 2B • Updated • 25Note ModelOpt FP8 for vLLM
Remek/basal-1.0-1.5B-NVFP4
Text Generation • 0.8B • Updated • 266Note ModelOpt NVFP4 for vLLM (Blackwell)