0 0 0 C++

bert : add tests + fix quantization (#5475)

* llama : do not quantize pos embd and token type tensors

* ci : add BERT tests

ggml-ci

* ci : do not do BERT tests on low-perf nodes

ggml-ci

Georgi Gerganov committed 2y ago

49cc1f7d67de2da99f3ac185f9ff1319b7bf35f8

Parent: 99b8b43

Committed by GitHub <noreply@github.com> on 2/13/2024, 11:01:29 AM