Georgi Gerganov b8fe4b5cc9 main : fix session loading bug (#3400)

2023-10-11 23:55:41 +03:00

..

baby-llama

…

batched

batched : add bench tool (#3545)

2023-10-11 21:25:33 +03:00

batched-bench

batched : add bench tool (#3545)

2023-10-11 21:25:33 +03:00

batched.swift

examples : add batched.swift + improve CI for swift (#3562)

2023-10-11 06:14:05 -05:00

beam-search

…

benchmark

…

convert-llama2c-to-ggml

…

embd-input

common : fix mirostat state when using multiple sequences (#3543)

2023-10-11 22:35:46 +03:00

embedding

…

export-lora

…

finetune

finetune : readme fix typo (#3465)

2023-10-04 09:33:13 +03:00

gguf

…

gptneox-wip

…

infill

common : fix mirostat state when using multiple sequences (#3543)

2023-10-11 22:35:46 +03:00

jeopardy

parallel : add option to load external prompt file (#3416)

2023-10-06 16:16:38 +03:00

llama-bench

…

main

main : fix session loading bug (#3400)

2023-10-11 23:55:41 +03:00

main-cmake-pkg

…

metal

…

parallel

common : fix mirostat state when using multiple sequences (#3543)

2023-10-11 22:35:46 +03:00

perplexity

…

quantize

…

quantize-stats

…

save-load-state

common : fix mirostat state when using multiple sequences (#3543)

2023-10-11 22:35:46 +03:00

server

server : add parameter -tb N, --threads-batch N (#3584)

2023-10-11 22:42:22 +03:00

simple

…

speculative

common : fix mirostat state when using multiple sequences (#3543)

2023-10-11 22:35:46 +03:00

train-text-from-scratch

…

alpaca.sh

…

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

llama : fix session saving/loading (#3400)

2023-10-03 21:04:01 +03:00

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

batched : add bench tool (#3545)

2023-10-11 21:25:33 +03:00

gpt4all.sh

…

json-schema-to-grammar.py

…

llama2-13b.sh

…

llama2.sh

…

llama.vim

…

llm.vim

…

make-ggml.py

…

Miku.sh

…

reason-act.sh

…

server-llama2-13B.sh

…