Georgi Gerganov
f477fb069b
llama : reorder definitions in .cpp to match .h
2023-08-15 22:29:56 +03:00
Georgi Gerganov
afd135a64c
llama : merge gguf-util.h in llama.cpp
2023-08-15 22:09:56 +03:00
Georgi Gerganov
a02b809a2e
llama : move hparams and vocab from gguf_file_loader to llama_model_loader
2023-08-15 21:09:27 +03:00
Georgi Gerganov
6c3f824697
llama : simplify gguf_file_loader
2023-08-15 20:53:53 +03:00
Georgi Gerganov
2906d5492d
gguf : remove obosolete gguf_get_arr_xxx API
2023-08-15 20:46:18 +03:00
Georgi Gerganov
1751bd4693
gguf : remove oboslete write methods
2023-08-15 20:41:53 +03:00
Georgi Gerganov
f7a6aa9911
gguf : streaming support when writing files
2023-08-15 19:57:37 +03:00
Georgi Gerganov
4ef5e792e3
llama : replace gguf_file_saver with new gguf write API
2023-08-15 18:29:42 +03:00
Georgi Gerganov
35177d735d
gguf : minor
2023-08-15 16:05:23 +03:00
Georgi Gerganov
c9b2f7f1bf
gguf : fixes + simplify example + add ggml_nbytes_pad()
2023-08-15 16:01:38 +03:00
Georgi Gerganov
4463965401
gguf : fix header write
2023-08-15 14:39:27 +03:00
Georgi Gerganov
f6ecd15f83
gguf : initial write API ready + example
2023-08-15 14:35:00 +03:00
Georgi Gerganov
85ebfb8e5d
gguf : write to file API (not tested)
2023-08-15 14:26:28 +03:00
Georgi Gerganov
5cb9d9a87f
gguf : initial write API (not tested yet)
2023-08-15 13:40:07 +03:00
M. Yusuf Sarıgöz
2d87c9c796
llama : refactor tensor names ( #2622 )
...
* gguf: update tensor names searched in quantization
* gguf : define tensor names as constants
2023-08-15 13:29:30 +03:00
Georgi Gerganov
da424b6699
llama : gguf_file_saver write I32
2023-08-15 11:31:42 +03:00
Georgi Gerganov
9574f41818
llama : no need to pass full file loader to the file saver
...
just gguf_ctx
2023-08-15 11:28:02 +03:00
Georgi Gerganov
5c85332e99
llama : simplify write_header()
2023-08-15 11:28:02 +03:00
Georgi Gerganov
6e29ed52fb
llama : fix method names
2023-08-15 11:28:02 +03:00
Georgi Gerganov
c9c0b758d4
llama : simplify gguf_file_saver
2023-08-15 11:28:02 +03:00
Georgi Gerganov
66ce19aecb
llama : fix quantization using gguf tool
2023-08-15 11:28:02 +03:00
Georgi Gerganov
a82e3a4d92
llama : style formatting + remove helper methods
2023-08-15 11:28:02 +03:00
klosax
2dd5d2c92c
convert-llama-h5-to-gguf.py : add 70b gqa support
2023-08-15 00:43:10 +02:00
klosax
ca4758290c
gguf-llama.cpp : fix n_head_kv
2023-08-14 23:18:41 +02:00
klosax
ab2cbd03ca
convert-llama-7b-pth-to-gguf.py : add token types
2023-08-14 22:10:50 +02:00
klosax
cedb4870c6
gguf.py : add token types
2023-08-14 22:08:40 +02:00
klosax
5d518d421f
constants.py : add token types
2023-08-14 22:07:53 +02:00
klosax
7ec125b1dc
convert-llama-h5-to-gguf.py : add token types
2023-08-14 22:06:33 +02:00
Georgi Gerganov
6c63550f63
llama : update tokenizer style
2023-08-14 22:11:57 +03:00
Georgi Gerganov
7494c78428
llama : sync gguf-llama with llama ( #2613 )
...
* llama : sync gguf-llama with llama
* tests : fix build + warnings (test-tokenizer-1 still fails)
* tests : fix wstring_convert
* convert : fix layer names
* llama : sync gguf-llama.cpp
* convert : update HF converter to new tokenizer voodoo magics
2023-08-14 21:33:33 +03:00
goerch
afc4ca2889
convert : update convert-new.py with tokenizer fixes ( #2614 )
...
* Merge tokenizer fixes into the gguf branch.
* Add test vocabularies
* Adapt convert-new.py (and fix a clang-cl compiler error on windows)
2023-08-14 20:20:04 +03:00
goerch
ec1b100720
llama : tokenizer fixes ( #2549 )
...
* Merge tokenizer fixes into the gguf branch.
* Add test vocabularies
2023-08-14 19:30:28 +03:00
Georgi Gerganov
8af3a99ff1
Merge branch 'master' into gguf
2023-08-14 16:39:18 +03:00
Georgi Gerganov
6f14854880
gitignore : add gptneox-main
2023-08-14 16:39:02 +03:00
Jhen-Jie Hong
d783f7982e
metal : return null instead of exit(1) ( #2573 )
2023-08-14 16:37:39 +03:00
Cheng Shao
d75561df20
server : add --numa support ( #2524 )
2023-08-14 16:36:42 +03:00
Kamil Tomšík
348acf188c
llama : add missing enum keyword in function signatures ( #2610 )
2023-08-14 16:35:16 +03:00
Georgi Gerganov
f00780b2ee
llama : sync gguf-llama.cpp with latest llama.cpp ( #2608 )
...
* llama : sync gguf-llama.cpp with latest llama.cpp
* minor : indentation + assert
* llama : refactor gguf_buffer and gguf_ctx_buffer
* llama : minor
2023-08-14 16:28:44 +03:00
klosax
6f64b6c0f8
Create convert-llama-7b-pth-to-gguf.py
2023-08-14 13:51:09 +02:00
Georgi Gerganov
62490f1380
gguf : use UNIX line ending
2023-08-14 13:04:35 +03:00
Georgi Gerganov
0c19ae70d5
simple : minor style changes
2023-08-14 12:58:12 +03:00
klosax
5c5a95ba2d
gguf.py : dont add empty strings
2023-08-14 11:22:06 +02:00
klosax
a7d226f871
convert-llama-h5-to-gguf.py : fixes
2023-08-14 11:14:24 +02:00
klosax
d753dfbcc8
gptneox-main.cpp : tensor name map changes
2023-08-14 10:59:18 +02:00
klosax
806a15749d
Delete gguf_tensor_map.py
2023-08-14 10:57:19 +02:00
klosax
51939d7d1b
Create gguf_namemap.py : tensor name map changes
2023-08-14 10:56:59 +02:00
klosax
5d22a9db13
convert-gptneox-h5-to-gguf.py : tensor name map changes
2023-08-14 10:55:44 +02:00
Johannes Gäßler
1cd06fa25e
CUDA: launch_bounds, small q4_K, q5_K mmq refactor ( #2596 )
2023-08-14 10:41:22 +02:00
Jhen-Jie Hong
2feb8934eb
server : fix default grammar by use empty string in the UI ( #2604 )
2023-08-14 16:20:17 +08:00
Jhen-Jie Hong
5517d6e692
server : implement json-schema-to-grammar.mjs & add grammar param in the UI ( #2588 )
...
* server : implement json-schema-to-grammar.mjs by follow python impl
* server : add grammar support in chat.mjs
* server : implement grammer param in the UI
* server : generate .hpp
* server : remove trailing whitespaces
* server : generate .hpp
* server : fix sort of prop pairs
* server : optimize regex & iteration
2023-08-14 15:16:54 +08:00
