LLM: tips untuk CPU
Revision as of 04:26, 17 July 2024 by Onnowpurbo (talk | contribs)
Kata CGPT: saat pake CPU, coba:
1. Batch Processing u. kurangi overhead & speedup embedding. 2. Kurangi presisi model; float32->float16/int8; speedup tanpa korbankan akurasi. 3. Buat versi kecil dari model yg sama. 4. Multi-threading. 5. Gunakan Intel MKL / OpenBLAS.
saya pakai model intfloat pak, lumayan cepet di CPU https://huggingface.co/intfloat/multilingual-e5-large
kalo pdf bisanya saya parse dulu textnya atau pakai ocr, terus embeddingnya disimpan di postgre pakai pgvector (https://github.com/pgvector/pgvector) agak effort sih