Releases: l3utterfly/llama.cpp
Releases · l3utterfly/llama.cpp
Layla v3.3.0
llama.cpp used in the Layla v3.3.0 release
Layla v3.2.0
Merge branch 'master' into layla-build
Layla v3.0.0
server : update readme about token probs (#4777) * updated server readme to reflect the gg/server-token-probs-4088 commit added explanation for the API's completion result which now includes `completion_probabilities`. Also added a JSON schema that shows the type/structure of `completion_probabilities`. * simplified the `completion_probabilities` JSON schema It's now easier to understand what the structure of `completion_probabilities` looks like. * minor : fix trailing whitespace --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Layla v2.0.0
Merge branch 'master' into layla-build
Layla v1.9.0
merged conflicts
Layla v1.8.0
Merge branch 'master' into layla-build
Layla v1.7.0
Merge branch 'master' into layla-build
Layla v1.5.1
samplers : Min-P sampler implementation [alternative to Top P/Top K] … …(#3841) * Introduce the new Min-P sampler by @kalomaze The Min-P sampling method was designed as an alternative to Top-P, and aims to ensure a balance of quality and variety. The parameter *p* represents the minimum probability for a token to be considered, relative to the probability of the most likely token. * Min-P enabled and set to 0.05 default --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
Layla v1.4.12
MPT : support GQA for replit-code-v1.5 (#3627)
Layla v1.4.11
fixed save_load_session on ios