 Zhang Peiyuan
|
e519621010
convert : remove bug in convert.py permute function (#3364)
|
2 lat temu |
 Erik Scholz
|
6eeb4d9083
convert: remove most of the n_mult usage in convert.py (#3098)
|
2 lat temu |
 Cebtenzzre
|
6336d834ec
convert : fix F32 ftype not being saved (#3048)
|
2 lat temu |
|
Erik Scholz
|
c9c3220c48
convert: fix convert.py not working with int filename_stem (#3028)
|
2 lat temu |
 Kerfuffle
|
cff7b0bf07
convert.py : BPE fixes (#2938)
|
2 lat temu |
|
Cebtenzzre
|
bce1fef328
convert : fix another python 3.8 issue (#2949)
|
2 lat temu |
|
Kerfuffle
|
aeefac4ff7
scripts: Use local gguf package when running from repo (#2927)
|
2 lat temu |
|
Cebtenzzre
|
92d0b751a7
convert : fix python 3.8 support, modernize type annotations (#2916)
|
2 lat temu |
 Georgi Gerganov
|
b532a69b2f
convert.py : use dir name to name the llama
|
2 lat temu |
|
Kerfuffle
|
dc07dc492e
convert : various script cleanups/fixes + merges and special token handling (#2842)
|
2 lat temu |
 jameswu2014
|
bcce96ba4d
convert.py : fix baichuan7B support (#2870)
|
2 lat temu |
|
Kerfuffle
|
730d9c681e
convert.py : advanced option (#2753)
|
2 lat temu |
 Nigel Bosch
|
a2ca4e9de9
Handle null rope scaling value (#2793)
|
2 lat temu |
|
Nigel Bosch
|
28b2c996ca
convert.py : Get rope scale from HuggingFace models (#2772)
|
2 lat temu |
 slaren
|
12e2e33a97
convert.py : export rope freq_base when converting CodeLlama from an HF model (#2773)
|
2 lat temu |
|
slaren
|
d0f77b1353
convert.py : try to determine n_ctx automatically for CodeLlama (#2770)
|
2 lat temu |
|
slaren
|
0d3094f0c7
gguf : add rope_freq_base parameter for CodeLlama (#2769)
|
2 lat temu |
|
Georgi Gerganov
|
8f8c28e89c
convert : auto-determine model name based on dir + scripts update
|
2 lat temu |
|
slaren
|
fea95c682d
fix convert.py for codellama, add llama 34B to the list of recognized models (#2768)
|
2 lat temu |
|
Georgi Gerganov
|
cf658adc83
llm : add Falcon support (#2717)
|
2 lat temu |
|
Cebtenzzre
|
7c2227a197
chmod : make scripts executable (#2675)
|
2 lat temu |
 Alex Petenchea
|
3b6cfe7c92
convert.py : clarifying error message (#2718)
|
2 lat temu |
|
Georgi Gerganov
|
deb7dfca4b
gguf : add ftype meta info to the model (#2710)
|
2 lat temu |
|
Georgi Gerganov
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 lat temu |
 Keiichi Tabata
|
2e8265ae17
convert.py : add missing abstract methods for quantized data (#2491)
|
2 lat temu |
 mj-shifu
|
7c529cede6
convert.py : Update to support 70B HF format model files (#2427)
|
2 lat temu |
 ldwang
|
fce48caf9a
convert.py : support bpe tokenizer (#2228)
|
2 lat temu |
|
Georgi Gerganov
|
e76d630df1
llama : grouped-query attention + LLaMAv2 70B support (#2276)
|
2 lat temu |
 wzy
|
b1f4290953
cmake : install targets (#2256)
|
2 lat temu |
 Aarni Koskela
|
3e08ae99ce
convert.py: add mapping for safetensors bf16 (#1598)
|
2 lat temu |
