Co-authored-by: Ebey Abraham <redacted>
python3 convert.py models/mymodel/
# [Optional] for models using BPE tokenizers
-python convert.py models/mymodel/ --vocabtype bpe
+python convert.py models/mymodel/ --vocab-type bpe
# quantize the model to 4-bits (using Q4_K_M method)
./quantize ./models/mymodel/ggml-model-f16.gguf ./models/mymodel/ggml-model-Q4_K_M.gguf Q4_K_M