Commits

History for

Commits on Dec 1, 2023

llama : add Qwen support (ggerganov#4281 )

simonJJJ
and
ggerganov
committedDec 1, 2023

Commits on Nov 20, 2023

ci : add flake8 to github actions (python linting) (ggerganov#4129 )
Galunid
committedNov 20, 2023

Commits on Nov 19, 2023

gguf-py : export chat templates (ggerganov#4125 )
slaren
committedNov 19, 2023

Commits on Nov 17, 2023

Respect tokenizer.ggml.add_bos_token value when tokenizing (ggerganov#4040 )
KerfuffleV2
committedNov 17, 2023

Commits on Nov 14, 2023

stablelm : StableLM support (ggerganov#3586 )
Galunid
committedNov 14, 2023

Commits on Nov 12, 2023

gguf-py: gguf_writer: Use bytearray to build metadata (ggerganov#4051 )
KerfuffleV2
committedNov 12, 2023

Commits on Nov 11, 2023

Fix gguf-convert-endian script (ggerganov#4037 )
monatis
committedNov 11, 2023
gguf-py: Refactor and allow reading/modifying existing GGUF files (ggerganov#3981 )

KerfuffleV2
and
cebtenzzre
committedNov 11, 2023

Commits on Nov 7, 2023

gguf : track writer state, free unneeded tensors, cleanup (ggerganov#3871 )
cebtenzzre
committedNov 7, 2023

Commits on Nov 4, 2023

gguf-py: Support 01.AI Yi models (ggerganov#3943 )
KerfuffleV2
committedNov 4, 2023

Commits on Nov 1, 2023

llama : implement YaRN RoPE scaling (ggerganov#2268 )

cebtenzzre
and
jquesnelle
committedNov 1, 2023

Commits on Oct 22, 2023

llama : validate special token ids are in range when loading GGUF model (ggerganov#3635 )

KerfuffleV2
and
ggerganov
committedOct 22, 2023

Commits on Oct 20, 2023

gguf : support big endian platform (ggerganov#3552 )

chenqiny
and
ggerganov
committedOct 20, 2023

Commits on Oct 10, 2023

llm : add bloom models (ggerganov#3553 )

xingchensong
and
ggerganov
committedOct 10, 2023

Commits on Oct 7, 2023

gguf.py : fix CI for publishing GGUF package (ggerganov#3532 )
monatis
committedOct 7, 2023
llm : support Adept Persimmon 8B (ggerganov#3410 )
phillip-kravtsov
committedOct 7, 2023

Commits on Oct 4, 2023

llm : add Refact model (ggerganov#3329 )

ds5t5
and
ggerganov
committedOct 4, 2023

Commits on Oct 2, 2023

gguf : add BERT, MPT, and GPT-J arch info (ggerganov#3408 )
cebtenzzre
committedOct 2, 2023
gguf : general usability improvements (ggerganov#3409 )
cebtenzzre
committedOct 2, 2023

Commits on Sep 27, 2023

gguf : fix a few general keys (ggerganov#3341 )
cebtenzzre
committedSep 27, 2023

Commits on Sep 15, 2023

llama : add support for StarCoder model architectures (ggerganov#3187 )

wsxiaoys
and
ggerganov
committedSep 15, 2023

Commits on Sep 14, 2023

gguf-py : support identity operation in TensorNameMap (ggerganov#3095 )
KerfuffleV2
committedSep 14, 2023
feature : support Baichuan serial models (ggerganov#3009 )
jameswu2014
committedSep 14, 2023

Commits on Sep 3, 2023

gguf(python): Fix special vocab handling when id < 0 (ggerganov#2984 )
KerfuffleV2
committedSep 3, 2023

Commits on Aug 31, 2023

convert : fix python 3.8 support, modernize type annotations (ggerganov#2916 )
cebtenzzre
committedAug 31, 2023

Commits on Aug 30, 2023

gguf : add workflow for Pypi publishing (ggerganov#2896 )
monatis
committedAug 30, 2023
convert : various script cleanups/fixes + merges and special token handling (ggerganov#2842 )
KerfuffleV2
committedAug 30, 2023

Commits on Aug 27, 2023

gguf : add 64-bit support (GGUF v2) (ggerganov#2821 )

ggerganov
and
klosax
committedAug 27, 2023

Commits on Aug 25, 2023

gguf : export objects to user code (ggerganov#2780 )
monatis
committedAug 25, 2023
gguf : make gguf pip-installable
monatis
committedAug 25, 2023

Loading