Georgi Gerganov 8f961abdc4 speculative : change default p_accept to 0.5 + CLI args (#3919) ...

ggml-ci

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

..

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

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

2023-11-02 08:50:16 +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

…

finetune

llama : implement YaRN RoPE scaling (#2268)

2023-11-01 18:04:33 -04:00

gguf

check C++ code with -Wmissing-declarations (#3184)

2023-09-15 15:38:27 -04:00

infill

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

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

jeopardy

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

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

llama-bench

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

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

llava

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

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

main

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

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

main-cmake-pkg

cmake : add missed dependencies (#3763)

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

metal

…

parallel

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

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

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

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

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

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

llama : implement YaRN RoPE scaling (#2268)

2023-11-01 18:04:33 -04:00

alpaca.sh

…

chat-13B.bat

…

chat-13B.sh

examples : read chat prompts from a template file (#1196)

2023-05-03 20:58:11 +03:00

chat-persistent.sh

…

chat-vicuna.sh

examples : add chat-vicuna.sh (#1854)

2023-06-15 21:05:53 +03:00

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

gitignore : changes for Poetry users + chat examples (#2284)

2023-07-21 13:53:27 +03:00

llama2.sh

gitignore : changes for Poetry users + chat examples (#2284)

2023-07-21 13:53:27 +03:00

llama.vim

vim : streaming and more (#2495)

2023-08-08 14:44:48 +03:00

llm.vim

llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)

2023-08-30 09:50:55 +03:00

make-ggml.py

…

Miku.sh

MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)

2023-07-21 11:13:18 +03:00

reason-act.sh

…

server-llama2-13B.sh

chmod : make scripts executable (#2675)

2023-08-23 17:29:09 +03:00