Georgi Gerganov ee1a0ec9cb llama : add option for greedy sampling with probs (#3813) ...

* llama : add option for greedy sampling with probs

* llama : add comment about llama_sample_token_greedy() missing probs

* sampling : temp == 0.0 -> no probs, temp < 0.0 -> probs

2023-10-28 14:23:11 +03:00

..

CMakeLists.txt

speculative : PoC for speeding-up inference via speculative sampling (#2926)

2023-09-03 15:12:08 +03:00

speculative.cpp

llama : add option for greedy sampling with probs (#3813)

2023-10-28 14:23:11 +03:00