vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
2453 commits 380 branches 3056 tags 365 MiB
Commit graph

2453 commits

This branch
This branch
All branches
Author SHA1 Message Date
Concedo
fafe999ff9 update lite and colab (+1 squashed commits) 
Squashed commits:

[06b6ca6d] updated lite and colab
 2023-10-22 14:03:18 +08:00
Georgi Gerganov
22c69a2794
batched : add len CLI argument 2023-10-22 08:37:20 +03:00
Concedo
cff75061fe fixed some old models failing due to tokenizer changes, update lite (+1 squashed commits) 
Squashed commits:

[9dee81ec] fixed some old models failing due to tokenizer changes, update lite tooltip (+3 squashed commit)

Squashed commit:

[5ab95a79] fixes

[a561d5e2] fixed some old models failing due to tokenizer changes

[95e65daf] lite updates
 2023-10-22 11:04:59 +08:00
Concedo
dd1d61ea6b colab is fixed (+1 squashed commits) 
Squashed commits:

[0b2a51f3] fix colab (+1 squashed commits)

Squashed commits:

[a6b832d0] fix colab (+1 squashed commits)

Squashed commits:

[8f88f210] updated colab (+1 squashed commits)

Squashed commits:

[75552e0d] try new colab
 2023-10-21 10:08:32 +08:00
shibe2
465219b914 CLBlast: Add outer loops over src0 for broadcasting in mulmat 
Reduce repeated dequantization of the same data.
 2023-10-20 22:30:52 +04:00
Georgi Gerganov
d1031cf49c
sampling : refactor init to use llama_sampling_params (#3696) 
* sampling : refactor init to use llama_sampling_params

* llama : combine repetition, frequency and presence penalties in 1 call

* examples : remove embd-input and gptneox-wip

* sampling : rename penalty params + reduce size of "prev" vector

* sampling : add llama_sampling_print helper

* sampling : hide prev behind API and apply #3661

ggml-ci
 2023-10-20 21:07:23 +03:00
Concedo
6119a2b5b2 revert lite change 2023-10-20 22:13:56 +08:00
Concedo
6fa681b692 fixed a race condition with SSE streaming 2023-10-20 22:01:09 +08:00
Concedo
5f5d5f1d86 quick fix 2023-10-20 19:43:56 +08:00
Qin Yue Chen
8cf19d60dc
gguf : support big endian platform (#3552) 
* check whether platform is 390x if yes->do not import immintrin.h

* support s390x big endian

* support --bigendian option for s390x
1. verified with baichuan7b-chat with float 16 on s390x
2. verified with baichuan7b-chat
3. verified with chinese-alpaca-2-13b-f16

* update format based on editor-config checker result

* Update convert-baichuan-hf-to-gguf.py

* 1. check in ggml.c if endianess is not match
2. update GGUF version
3. change get_pack_prefix to property
4. update information log

* always use "GGUF" as beginng of GGUF file

* Compare "GGUF" with file header char by char
1.  Set GGUF_MAGIC to "GGUF" string instead of int value
2. Compare "GGUF" char by char to ensure its byte order
3. Move bytes swap code from convert.py to gguf.py write_tensor_data

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-10-20 14:19:40 +03:00
Concedo
012c53367d minor lite fixes 2023-10-20 18:41:17 +08:00
Georgi Gerganov
a0edf73bda
server : fix uninitialized sampling context (close #3685) 2023-10-20 13:06:10 +03:00
Herman Semenov
f439e506e8
ggml : fix rope + llama minor optimizations (#3560) 
* Minor fixes and fixed memleak

* Using const auto references in range-based loop C++17
 2023-10-20 13:02:12 +03:00
Concedo
d3c7b7cc71 colab fix 2023-10-20 16:34:45 +08:00
Concedo
d5016fdc8f updated lite bug 2023-10-20 16:03:06 +08:00
Concedo
ee93213218 updated lite 2023-10-20 15:44:52 +08:00
Concedo
cd3bb3ede2 update colab link 2023-10-20 13:49:34 +08:00
cebtenzzre
e78f3ef24a
convert : restore compat with old Falcon models (#3680) 2023-10-20 08:32:08 +03:00
Concedo
8947142c46 updated lite and colab 2023-10-20 11:35:44 +08:00
M. Yusuf Sarıgöz
f3b25e4043
multimodal : add BakLLaVA conversion support (#3682) 2023-10-19 19:40:41 +03:00
Concedo
8d31550d48 fix groupchat 2023-10-19 23:40:15 +08:00
Concedo
957e245285 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	Makefile
#	README.md
 2023-10-19 23:32:52 +08:00
kalomaze
ddce116ec9
Fix for Top K disabling (#480) 
* Update gpttype_adapter.cpp

* use n_vocab instead of 32000 for when top k is off
 2023-10-19 23:20:44 +08:00
Concedo
8c6001de2a updated lite 2023-10-19 23:18:14 +08:00
Concedo
fd770bb105 patch 2023-10-19 23:04:26 +08:00
Concedo
4382e51719 updated lite and default horde ctx amount 2023-10-19 22:49:59 +08:00
M. Yusuf Sarıgöz
60abea9798
llava : avoid segfault in case of non-existent mmproj file (#3674) 2023-10-19 16:59:11 +03:00
Georgi Gerganov
004797f6ac
readme : update hot topics 2023-10-18 21:44:43 +03:00
Georgi Gerganov
4e82b2ea3f
speculative : bug fixes 2023-10-18 18:49:40 +03:00
Georgi Gerganov
0e89203b51
speculative : add tree-based sampling example (#3624) 
* sampling : one sequence per sampling context

ggml-ci

* speculative : add tree-based sampling support

ggml-ci

* speculative : reuse the n_parallel CLI param

* speculative : refactor sampling

* examples : fix build after sampling refactoring

ggml-ci

* batched : fix n_seq_id

* sampling : fix malloc

ggml-ci

* swift : fix build

ggml-ci

* swift : try to fix build

ggml-ci

* prompts : add assistant.txt

* common : add llama_batch_add() and llama_batch_clear() helpers

* speculative : minor refactor

ggml-ci

* minor : comments + rename

ggml-ci

* speculative : fix off-by-one for n_drafted

* speculative : fix the n_drafted fix + p constants
 2023-10-18 16:21:57 +03:00
Jhen-Jie Hong
c67fe68e41
metal : implement q5_0 and q5_1 kernels (#3648) 
* metal : implement dequantize_q5_0

* metal : block_q_n_dot_y for block_q5_0 (broken)

* metal : revert unnecessary change

* metal : implement dequantize_q5_1

* metal : block_q_n_dot_y for q5_1 (broken)

* metal : fix block_q_n_dot_y

* minor : spaces / formatting

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-10-18 15:21:48 +03:00
shibe2
1117d06607
opencl : fix element-wise multiplication (#3656) 2023-10-18 15:09:22 +03:00
Concedo
c1ca1de2ac fixed support for old falcon models 2023-10-18 17:20:44 +08:00
Concedo
700951dbd4 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	README.md
 2023-10-18 16:33:09 +08:00
Concedo
53b7cdf8a3 Merge branch 'concedo' into concedo_experimental 2023-10-18 13:51:13 +08:00
slaren
cb33f43a2a
fix embeddings when using CUDA (#3657) 2023-10-17 22:24:50 +02:00
Georgi Gerganov
e1675d133c
llama : avoid fprintf in favor of LLAMA_LOG (#3538) 2023-10-17 22:34:26 +03:00
BarfingLemurs
8402566a7c
readme : update hot-topics & models, detail windows release in usage (#3615) 
* Update README.md

* Update README.md

* Update README.md

* move "Running on Windows" section below "Prepare data and run"

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-10-17 21:13:21 +03:00
LostRuins
6e34d31c44
Update README.md (#479) 2023-10-18 01:24:14 +08:00
shibe2
40e5ce054f CLBlast: Fix temporary buffer size for f16 conversion (wsize) 
Fix buffer overflow.
Reduce the size to fit just one 2D slice.
Assert sufficient size.
 2023-10-17 21:02:30 +04:00
slaren
a5e8c1d8c7
train-text-from-scratch : fix assert failure in ggml-alloc (#3618) 2023-10-17 20:00:58 +03:00
Georgi Gerganov
e74c705e15
editorconfig : remove trailing spaces 2023-10-17 19:52:53 +03:00
coezbek
3ad1e3f1a1
server : documentation of JSON return value of /completion endpoint (#3632) 
* Added documentation of JSON return value of /completion endpoint

* Update examples/server/README.md

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-10-17 19:51:02 +03:00
Georgi Gerganov
1142013da4
save-load-state : fix example + add ci test (#3655) 
* save-load-state : fix example (close #3606)

* ci : add test for save-load-state example

ggml-ci
 2023-10-17 19:12:46 +03:00
ldwang
5fe268a4d9
readme : add Aquila2 links (#3610) 
Signed-off-by: ldwang <ftgreat@gmail.com>
Co-authored-by: ldwang <ftgreat@gmail.com>
 2023-10-17 18:52:33 +03:00
staviq
1a159553f9
tokenizer : special token handling (#3538) 
* Rewrite special token handling from #1931

* shorten param name, add st verification by type

* use offsets instead of copy by substr

* formatting, remove copying iterator on delete

* llama : normalize code-style

* swift fix

* print pfx/sfx if verb, main: split pfx input sfx

* dont add space when using special tokens

* minor : comment + spacing

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-10-17 18:11:01 +03:00
Concedo
6f8fe88f10 fix for lite (+5 squashed commit) 
Squashed commit:

[f9ce9855] catch more exceptions

[8cdaf149] tweaked horde worker timeouts, updated lite

[619ebef4] fixed abort no response if failed

[a54a66a2] fixed time overflow

[9affdc3e] updated lite
 2023-10-17 23:04:32 +08:00
Georgi Gerganov
281ef73c25
k-quants : fix quantization ranges (#3646) 2023-10-17 09:19:28 +03:00
Georgi Gerganov
940efa95fe
llava : fix tokenization to not add bos between image embeddings and user prompt (#3645) 
* llava : fix tokenization to not add bos after system prompt

* set seed

---------

Co-authored-by: M. Yusuf Sarıgöz <yusufsarigoz@gmail.com>
 2023-10-16 23:58:00 +03:00
Concedo
ee0681f0d9 convert some asserts into non-terminating since they are ovezealous 2023-10-15 16:12:20 +08:00