diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2024-01-18 15:33:01 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-18 15:33:01 +0200 |
| commit | ad19812cda4062c9f154ef16315df41fbe6a770a (patch) | |
| tree | 0ce3a8f8e16fb077d614ed2554aff32e82eb61c5 /examples/quantize-stats | |
| parent | 682986a08eb5cb04865d2e713449f17304d266d8 (diff) | |
perplexity : faster HellaSwag via batching (#5017)
* perplexity : faster HellaSwag
ggml-ci
* perplexity : clean-up
ggml-ci
* perplexity : no need for decode_helper
ggml-ci
* perplexity : add comments
* perplexity : option to specify max batched tasks via `n_parallel`
* perplexity : remove HellaSwag restruction for n_batch
Diffstat (limited to 'examples/quantize-stats')
0 files changed, 0 insertions, 0 deletions