ochafik/llama.cpp

Pull Requests Commits

llama2.c: convert special-cased "<0xXX>" single byte tokens from tokenizer.bin

ochafik committed 2 years ago

8d0dc476

llama2.c: comment out legacy "load from ggml model" logic

ochafik committed 2 years ago

8ad1e2d8

llama2c: reinstate ggmlv3 conversion output + update readme w/ gguf conv

ochafik committed 2 years ago

59f67c69

Fix import of llama2.c models that don't share weights between embedding layers

ochafik committed 2 years ago

0f7cb953

Fix convert-llama-ggmlv3-to-gguf.py vocab conversion (#2698)

KerfuffleV2 committed 2 years ago

Verified 930523c8

py : remove obsolete script

ggerganov committed 2 years ago

Verified c8dba409

gguf : new file format with flexible meta data (beta) (#2398)

ggerganov committed 2 years ago

Verified 6381d4e1

metal : fix synchronization in new matrix multiplication kernel (#2686)

lshzh-ww committed 2 years ago

Verified dadbed99

HellaSwag: split token evaluation into batches if needed (#2681)

ikawrakow committed 2 years ago

Verified cb1c0727

ggml : move all type info to ggml_type_traits (#2663)

slaren committed 2 years ago

Verified 9e232f02

More efficient Hellaswag implementation (#2677)

ikawrakow committed 2 years ago

Verified 5e9ff54a

server : better default prompt (#2646)

ggerganov committed 2 years ago

Verified 1f0bccb2

server : update xxd usage for older versions compatibility (#2649)

jhen0409 committed 2 years ago

Verified f63564ad

Add link to clojure bindings to Readme. (#2659)

phronmophobic committed 2 years ago

Verified 2d8b76a1

readme : incoming BREAKING CHANGE

ggerganov committed 2 years ago

Verified 7af633ae

llama : add benchmark example (#2626)

slaren committed 2 years ago

Verified 097e121e

readme : add link to Rust bindings (#2656)

mdrokz committed 2 years ago

Verified eaf98c26

perplexity : more meaningful ETA number - 2 decimal points

ggerganov committed 2 years ago

Verified e9b12c33

Fix unicode in grammars (fixes #2501) (#2553)

ejones committed 2 years ago

Verified 604b8bdf

server : support for saving templates in browser LocalStorage (#2486)

staviq committed 2 years ago

Verified 10151bee

README: fix LLAMA_CUDA_MMV_Y documentation (#2647)

JohannesGaessler committed 2 years ago

Verified 0992a7b8

[Zig] Fixing Zig build and improvements (#2554)

SlyEcho committed 2 years ago

Verified 6ddeefad

Add --cfg-negative-prompt-file option for examples (#2591)

KerfuffleV2 committed 2 years ago

Verified 8dae7ce6

llama : replace (permute + reshape + view_1d) with (view_3d) (#2538)

ggerganov committed 2 years ago

Verified a73ccf1a

tests : adds simple llama grammar tests (#2618)

drbh committed 2 years ago

Verified 7cf54e1f

ggml-alloc : fix discrepency between measure&eval (#2639)

lshzh-ww committed 2 years ago

Verified a872a2b2

cmake : install ggml-meta.metal if LLAMA_METAL (#2449)

ickc committed 2 years ago

Verified 0919a0f7

metal : print error of load pipeline state (#2564)

jhen0409 committed 2 years ago

Verified ed53db86

metal : enable ggml-alloc (#2627)

lshzh-ww committed 2 years ago

Verified fc8ef549

metal : matrix-matrix multiplication kernel (#2615)

lshzh-ww committed 2 years ago

Verified bf83bff6

Older