7744aa6a9c
updated colab
2023-10-24 15:37:47 +08:00
5f1f8a5a89
adjust
2023-10-22 21:53:54 +08:00
ccf8334651
remove script (+8 squashed commit)
...
Squashed commit:
[bde2e3da] should be working
[1cde82c0] update
[bb6c8676] wip
[66b698d1] wip colab
[9953466a] wip colab
[ae0bedea] json fix
[0aac144f] wip on optimized colab
[ec9f8e96] prepare colab binaries notebook
2023-10-22 21:38:38 +08:00
fafe999ff9
update lite and colab (+1 squashed commits)
...
Squashed commits:
[06b6ca6d] updated lite and colab
2023-10-22 14:03:18 +08:00
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
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
6119a2b5b2
revert lite change
2023-10-20 22:13:56 +08:00
6fa681b692
fixed a race condition with SSE streaming
2023-10-20 22:01:09 +08:00
5f5d5f1d86
quick fix
2023-10-20 19:43:56 +08:00
012c53367d
minor lite fixes
2023-10-20 18:41:17 +08:00
d3c7b7cc71
colab fix
2023-10-20 16:34:45 +08:00
d5016fdc8f
updated lite bug
2023-10-20 16:03:06 +08:00
ee93213218
updated lite
2023-10-20 15:44:52 +08:00
cd3bb3ede2
update colab link
2023-10-20 13:49:34 +08:00
8947142c46
updated lite and colab
2023-10-20 11:35:44 +08:00
8d31550d48
fix groupchat
2023-10-19 23:40:15 +08:00
957e245285
Merge branch 'master' into concedo_experimental
...
# Conflicts:
# Makefile
# README.md
2023-10-19 23:32:52 +08:00
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
8c6001de2a
updated lite
2023-10-19 23:18:14 +08:00
fd770bb105
patch
2023-10-19 23:04:26 +08:00
4382e51719
updated lite and default horde ctx amount
2023-10-19 22:49:59 +08:00
60abea9798
llava : avoid segfault in case of non-existent mmproj file ( #3674 )
2023-10-19 16:59:11 +03:00
004797f6ac
readme : update hot topics
2023-10-18 21:44:43 +03:00
4e82b2ea3f
speculative : bug fixes
2023-10-18 18:49:40 +03:00
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
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
1117d06607
opencl : fix element-wise multiplication ( #3656 )
2023-10-18 15:09:22 +03:00
c1ca1de2ac
fixed support for old falcon models
2023-10-18 17:20:44 +08:00
700951dbd4
Merge branch 'master' into concedo_experimental
...
# Conflicts:
# README.md
2023-10-18 16:33:09 +08:00
53b7cdf8a3
Merge branch 'concedo' into concedo_experimental
2023-10-18 13:51:13 +08:00
cb33f43a2a
fix embeddings when using CUDA ( #3657 )
2023-10-17 22:24:50 +02:00
e1675d133c
llama : avoid fprintf in favor of LLAMA_LOG ( #3538 )
2023-10-17 22:34:26 +03:00
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
6e34d31c44
Update README.md ( #479 )
2023-10-18 01:24:14 +08:00
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
a5e8c1d8c7
train-text-from-scratch : fix assert failure in ggml-alloc ( #3618 )
2023-10-17 20:00:58 +03:00
e74c705e15
editorconfig : remove trailing spaces
2023-10-17 19:52:53 +03:00
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
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
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
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
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
281ef73c25
k-quants : fix quantization ranges ( #3646 )
2023-10-17 09:19:28 +03:00
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
ee0681f0d9
convert some asserts into non-terminating since they are ovezealous
2023-10-15 16:12:20 +08:00
5cfabaee25
Merge branch 'master' into concedo_experimental
...
# Conflicts:
# CMakeLists.txt
# Makefile
# README.md
# docs/BLIS.md
2023-10-15 15:50:20 +08:00
11bff29045
MPT : support GQA for replit-code-v1.5 ( #3627 )
2023-10-15 09:32:06 +03:00
11dc1091f6
Honor -ngl option for Cuda offloading in llava ( #3621 )
2023-10-14 04:52:44 -06:00
2a4bcbacea
llama : remove n_threads from llama_decode_internal ( #3614 )
...
This commit removes `n_threads` from the `llama_decode_internal`
functions doc comment as it does not exist anymore.
It looks like this parameter was removed in
Commit 16bc66d947daniel.bevenius@gmail.com >
2023-10-13 13:33:16 +03:00
424b6381c4
ggml : add context enumeration functions ( #3605 )
...
finetune : fix assert failure in ggml-alloc
2023-10-13 12:23:10 +02:00
Concedo
kalomaze
M. Yusuf Sarıgöz
Georgi Gerganov
Jhen-Jie Hong
shibe2
slaren
BarfingLemurs
coezbek
ldwang
staviq
cebtenzzre
Daniel Bevenius