Commit Graph

34 Commits

Author SHA1 Message Date
Adam Treat
a41bd6ac0a Trying to shrink the copy+paste code and do more code sharing between backend model impl. 2023-06-02 07:20:59 -04:00
Tim Miller
87cb3505d3 Fix MSVC Build, Update C# Binding Scripts 2023-06-01 14:24:23 -04:00
niansa/tuxifan
27e80e1d10
Allow user to specify custom search path via $GPT4ALL_IMPLEMENTATIONS_PATH (#789) 2023-06-01 17:41:04 +02:00
niansa
5175db2781 Fixed double-free in LLModel::Implementation destructor 2023-06-01 11:19:08 -04:00
niansa/tuxifan
fc60f0c09c
Cleaned up implementation management (#787)
* Cleaned up implementation management

* Initialize LLModel::m_implementation to nullptr

* llmodel.h: Moved dlhandle fwd declare above LLModel class
2023-06-01 16:51:46 +02:00
Adam Treat
1eca524171 Add fixme's and clean up a bit. 2023-06-01 07:57:10 -04:00
niansa
a3d08cdcd5 Dlopen better implementation management (Version 2) 2023-06-01 07:44:15 -04:00
niansa/tuxifan
92407438c8
Advanced avxonly autodetection (#744)
* Advanced avxonly requirement detection
2023-05-31 21:26:18 -04:00
AT
48275d0dcc
Dlopen backend 5 (#779)
Major change to the backend that allows for pluggable versions of llama.cpp/ggml. This was squashed merged from dlopen_backend_5 where the history is preserved.
2023-05-31 17:04:01 -04:00
Adam Treat
7f9f91ad94 Revert "New tokenizer implementation for MPT and GPT-J"
This reverts commit bbcee1ced5.
2023-05-30 12:59:00 -04:00
Adam Treat
cdc7d6ccc4 Revert "buf_ref.into() can be const now"
This reverts commit d59c77ac55.
2023-05-30 12:58:53 -04:00
Adam Treat
b5edaa2656 Revert "add tokenizer readme w/ instructions for convert script"
This reverts commit 5063c2c1b2.
2023-05-30 12:58:18 -04:00
aaron miller
5063c2c1b2 add tokenizer readme w/ instructions for convert script 2023-05-30 12:05:57 -04:00
Aaron Miller
d59c77ac55 buf_ref.into() can be const now 2023-05-30 12:05:57 -04:00
Aaron Miller
bbcee1ced5 New tokenizer implementation for MPT and GPT-J
Improves output quality by making these tokenizers more closely
match the behavior of the huggingface `tokenizers` based BPE
tokenizers these models were trained with.

Featuring:
 * Fixed unicode handling (via ICU)
 * Fixed BPE token merge handling
 * Complete added vocabulary handling
2023-05-30 12:05:57 -04:00
Adam Treat
474c5387f9 Get the backend as well as the client building/working with msvc. 2023-05-25 15:22:45 -04:00
Adam Treat
9bfff8bfcb Add new reverse prompt for new localdocs context feature. 2023-05-25 11:28:06 -04:00
Juuso Alasuutari
ef052aed84 llmodel: constify some casts in LLModelWrapper 2023-05-22 08:54:46 -04:00
Juuso Alasuutari
81fdc28e58 llmodel: constify LLModel::threadCount() 2023-05-22 08:54:46 -04:00
Juuso Alasuutari
08ece43f0d llmodel: fix wrong and/or missing prompt callback type
Fix occurrences of the prompt callback being incorrectly specified, or
the response callback's prototype being incorrectly used in its place.

Signed-off-by: Juuso Alasuutari <juuso.alasuutari@gmail.com>
2023-05-21 16:02:11 -04:00
Adam Treat
8204c2eb80 Only default mlock on macOS where swap seems to be a problem. 2023-05-21 10:27:04 -04:00
Adam Treat
aba1147a22 Always default mlock to true. 2023-05-20 21:16:15 -04:00
aaron miller
e6fd0a240d backend: fix buffer overrun in repeat penalty code
Caught with AddressSanitizer running a basic prompt test against llmodel
standalone. This fix allows ASan builds to complete a simple prompt
without illegal accesses but there are still notably several leaks.
2023-05-17 07:54:10 -04:00
kuvaus
26cb31c4e6 Bugfix on llmodel_model_create function
Fixes the bug where llmodel_model_create prints "Invalid model file" even though the model is loaded correctly. Credits and thanks to @serendipity for the fix.
2023-05-17 07:49:32 -04:00
kuvaus
3cb6dd7a66
gpt4all-backend: Add llmodel create and destroy functions (#554)
* Add llmodel create and destroy functions

* Fix capitalization

* Fix capitalization

* Fix capitalization

* Update CMakeLists.txt

---------

Co-authored-by: kuvaus <kuvaus@users.noreply.github.com>
2023-05-16 11:36:46 -04:00
kuvaus
507e913faf
gpt4all-backend: Add MSVC support to backend (#595)
* Add MSVC compatibility

* Add _MSC_VER macro

---------

Co-authored-by: kuvaus <kuvaus@users.noreply.github.com>
2023-05-16 11:35:33 -04:00
Aaron Miller
d14936bfd6 backend: dedupe tokenizing code in mpt/gptj 2023-05-16 10:30:19 -04:00
Aaron Miller
6182026c70 backend: dedupe tokenizing code in gptj/mpt 2023-05-16 10:30:19 -04:00
Aaron Miller
4cd8bdf9a1 backend: make initial buf_size const in model impls
more unifying mpt and gptj code - this one's never written so also
changing the name to be clearer
2023-05-16 10:30:19 -04:00
Aaron Miller
08402a1b64 mpt: use buf in model struct (thread safety) 2023-05-16 10:30:19 -04:00
AT
4920816c90
Update README.md
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-05-14 15:26:00 -04:00
Zach Nussbaum
1ed71fbbf8 fix: use right conversion script 2023-05-11 11:20:43 -04:00
Adam Treat
d918b02c29 Move the llmodel C API to new top-level directory and version it. 2023-05-10 11:46:40 -04:00
Richard Guo
02d1bdb0be mono repo structure 2023-05-01 15:45:23 -04:00