Parakon
/

parakon-runtime

Model card Files Files and versions

parakon-runtime / examples /model-conversion /scripts /causal

18.3 kB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

kat0012's picture

Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3)

7011d4a verified 18 days ago

compare-embeddings-logits.sh

1.25 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 18 days ago
compare-logits.py

3.23 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 18 days ago
convert-model.sh

1.43 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 18 days ago
modelcard.template

185 Bytes
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 18 days ago
run-casual-gen-embeddings-org.py

4.24 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 18 days ago
run-converted-model-embeddings-logits.sh

636 Bytes
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 18 days ago
run-converted-model.sh

822 Bytes
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) 18 days ago
run-org-model.py

6.49 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) 18 days ago