M. Yusuf Sarıgöz bd90eca237 llava : fix regression for square images in #3613 (#4056)

2023-11-13 18:20:52 +03:00

..

baby-llama

…

batched

cuda : add batched cuBLAS GEMM for faster attention (#3749)

2023-10-24 16:48:37 +03:00

batched-bench

Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843)

2023-10-29 11:31:40 -06:00

batched.swift

…

beam-search

llama : remove token functions with context args in favor of model (#3720)

2023-10-23 22:40:03 +03:00

benchmark

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00

convert-llama2c-to-ggml

gguf : support big endian platform (#3552)

2023-10-20 14:19:40 +03:00

embedding

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

export-lora

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00

finetune

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00

gguf

…

infill

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

jeopardy

…

llama-bench

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

llava

llava : fix regression for square images in #3613 (#4056)

2023-11-13 18:20:52 +03:00

main

Fix some documentation typos/grammar mistakes (#4032)

2023-11-11 23:04:58 -07:00

main-cmake-pkg

cmake : add missed dependencies (#3763)

2023-10-24 20:48:45 +03:00

metal

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00

parallel

Fix some documentation typos/grammar mistakes (#4032)

2023-11-11 23:04:58 -07:00

perplexity

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

quantize

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

quantize-stats

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

save-load-state

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

server

server : fix crash when prompt exceeds context size (#3996)

2023-11-10 23:48:21 -06:00

simple

simple : fix batch handling (#3803)

2023-10-27 08:37:41 -06:00

speculative

speculative : change default p_accept to 0.5 + CLI args (#3919)

2023-11-03 09:41:56 +02:00

train-text-from-scratch

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00

alpaca.sh

…

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

…

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

sampling : refactor init to use llama_sampling_params (#3696)

2023-10-20 21:07:23 +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

…