mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-08-10 08:55:44 +00:00
a6aa6f5450
* Resolve -1 to 1024 instead of ctx-len for samplers Because of backend-sampling we initialize samplers before the complete llama_context is there. Therefore, we cannot infer the resolved context length yet at the time we construct the samplers. * Shared default of 64 for history-based samplers, remove context_size |
||
|---|---|---|
| .. | ||
| test-1-ground-truth.txt | ||
| test-1-positive.png | ||
| test-deepseek-ocr.py | ||
| tests-requirements.txt | ||
