ochafik/llama.cpp

Pull Requests Commits

grammars: simpler syntax (no swap)

Olivier Chafik committed 1 year ago

1e0f4669

grammars: update gbnf-validator.cpp

Olivier Chafik committed 1 year ago

cb77a8db

grammars: fix test (api changed)

Olivier Chafik committed 1 year ago

db787a44

grammars: fix missing sig change in llama.h

Olivier Chafik committed 1 year ago

763b41e2

grammars: reuse new_stacks

Olivier Chafik committed 1 year ago

47e37dd9

grammars: reserve rejects & next candidates

Olivier Chafik committed 1 year ago

3732ad9c

scripts : add --outdir option to hf.sh (#6600)

danbev committed 1 year ago

Verified f4183afe

eval-callback: Example how to use eval callback for debugging (#6576)

phymbert committed 1 year ago

Verified b804b1ef

gguf : add option to not check tensor data (#6582)

danbev committed 1 year ago

Verified 8228b66d

minor layout improvements (#6572)

rsoika committed 1 year ago

Verified b3a96f27

llama : add model types for mixtral (#6589)

slaren committed 1 year ago

Verified 4f407a0a

convert.py : add consolidated.safetensors for mixtral 8x22b (#6587)

slaren committed 1 year ago

Verified 65c64dc3

docs : how to add a model (#6565)

phymbert committed 1 year ago

Verified 67fac4b9

readme : fix ROCm link (#6579)

artem-zinnatullin committed 1 year ago

Verified 29122d32

readme : update UI list (#6560)

ylsdamxssjxxdd committed 1 year ago

Verified b231b37b

readme: fix typo in amdgpu target name (#6573)

Sejsel committed 1 year ago

Verified ba5e134e

BERT tokenizer fixes (#6498)

cebtenzzre committed 1 year ago

Verified 1b67731e

ggerganov committed 1 year ago

Verified c4a3a4ff

server : detect search query to start webchat (#6554)

Mardak committed 1 year ago

Verified 400d5d72

llama : add Command R Plus support (#6491)

RefractAI committed 1 year ago

Verified 5dc9dd71

license : update copyright notice + add AUTHORS (#6405)

ggerganov committed 1 year ago

Verified e11a8999

llama : fix attention layer count sanity check (#6550)

ggerganov committed 1 year ago

Verified cc4a9542

Comment explaining a decision (#6531)

kunnis committed 1 year ago

Verified cecd8d3c

quantize : fix precedence of cli args (#6541)

ggerganov committed 1 year ago

Verified b73e564b

llama : support negative ith in llama_get_ API (#6519)

TheFlipbook committed 1 year ago

Verified e3c337d8

llama : save and restore kv cache for single seq id (#6341)

kaetemi committed 1 year ago

Verified beea6e1b

remove row=1 cond (#6532)

abhilash1910 committed 1 year ago

Verified 87fb5b42

Adding KodiBot to UI list (#6535)

firatkiral committed 1 year ago

Verified d752327c

Change Windows AMD example to release build to make inference much faster. (#6525)

thebaron88 committed 1 year ago

Verified 855f5440

flake.lock: Update (#6517)

ggerganov committed 1 year ago

Verified b909236c

Older