Georgi Gerganov 38016ed9ec Merge branch 'master' into gguf

2023-08-18 15:21:48 +03:00

..

baby-llama

…

benchmark

…

convert-llama2c-to-ggml

gguf : deduplicate (#2629)

2023-08-16 19:25:29 +03:00

embd-input

…

embedding

llama : tokenizer fixes (#2549)

2023-08-14 19:30:28 +03:00

gguf

examples/gguf : no need to keep q option for quantization any more

2023-08-17 08:56:42 +03:00

gptneox-wip

gptneox : move as a WIP example

2023-08-17 19:49:45 +03:00

jeopardy

…

llama-bench

Merge branch 'master' into gguf

2023-08-18 15:21:48 +03:00

main

gguf : deduplicate (#2629)

2023-08-16 19:25:29 +03:00

metal

ci : update ".bin" to ".gguf" extension

2023-08-17 19:32:14 +03:00

perplexity

perplexity : more meaningful ETA number - 2 decimal points

2023-08-18 12:48:55 +03:00

quantize

gguf : deduplicate (#2629)

2023-08-16 19:25:29 +03:00

quantize-stats

quantize-stats.cpp : .bin --> .gguf

2023-08-17 19:18:24 +02:00

save-load-state

gguf : deduplicate (#2629)

2023-08-16 19:25:29 +03:00

server

Merge branch 'master' into gguf

2023-08-18 12:38:05 +03:00

simple

gguf : deduplicate (#2629)

2023-08-16 19:25:29 +03:00

train-text-from-scratch

gguf : deduplicate (#2629)

2023-08-16 19:25:29 +03:00

alpaca.sh

…

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

…

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

llama : add benchmark example (#2626)

2023-08-18 12:44:58 +02:00

common.cpp

Merge branch 'master' into gguf

2023-08-17 19:04:59 +03:00

common.h

common.h : .bin --> .gguf

2023-08-17 19:16:35 +02:00

console.cpp

…

console.h

…

gpt4all.sh

…

grammar-parser.cpp

…

grammar-parser.h

…

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

…