Commit Graph

841 Commits

Author SHA1 Message Date
aaron miller
9c15d1f83e add tokenizer readme w/ instructions for convert script 2023-05-30 12:05:57 -04:00
Aaron Miller
840e011b75 buf_ref.into() can be const now 2023-05-30 12:05:57 -04:00
Aaron Miller
ee3469ba6c 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
Andriy Mulyar
7e18f179e9 Improved localdocs documentation (#762)
* Improved localdocs documentation

* Improved localdocs documentation

* Improved localdocs documentation

* Improved localdocs documentation
2023-05-30 11:26:34 -04:00
Andriy Mulyar
3bb19b5e91 LocalDocs documentation initial (#761)
* LocalDocs documentation initial
2023-05-30 08:35:26 -04:00
mvenditto
522dfdbfe1 C# Bindings - Prompt formatting (#712)
* Added support for custom prompt formatting

* more docs added

* bump version
2023-05-28 19:57:00 -04:00
Chase McDougall
8189aece48 fix(training instructions): model repo name (#728)
Signed-off-by: Chase McDougall <chasemcdougall@hotmail.com>
2023-05-28 19:56:24 -04:00
Nandakumar
4161bfba33 Update README.md (#738)
* Update README.md

fix golang gpt4all import path

Signed-off-by: Nandakumar <nandagunasekaran@gmail.com>

* Update README.md

Signed-off-by: Nandakumar <nandagunasekaran@gmail.com>

---------

Signed-off-by: Nandakumar <nandagunasekaran@gmail.com>
2023-05-28 19:51:11 -04:00
Joseph Mearman
6ec2e26cd1 tiny typo (#739) 2023-05-28 19:50:45 -04:00
Richard Guo
9f62d4d05f hotfix default verbose optioin 2023-05-26 12:49:32 -04:00
Konstantin Gukov
6ec3efa355 one funcion to append .bin suffix 2023-05-26 09:24:03 -04:00
Konstantin Gukov
52efd17165 Correct indentation of the multiline error message 2023-05-26 09:24:03 -04:00
Konstantin Gukov
39bdd74ddd Add optional verbosity 2023-05-26 09:24:03 -04:00
Konstantin Gukov
136a5ac30d Correct return type 2023-05-26 09:24:03 -04:00
Konstantin Gukov
e362e18431 Do not ignore explicitly passed 4 threads 2023-05-26 09:24:03 -04:00
Konstantin Gukov
a2e2a64899 Redundant else 2023-05-26 09:24:03 -04:00
Konstantin Gukov
8229bb5477 1. Cleanup the interrupted download
2. with-syntax
2023-05-26 09:24:03 -04:00
Konstantin Gukov
b12e0e98c7 less magic number 2023-05-26 09:24:03 -04:00
Konstantin Gukov
4dff67cee5 convert to f-strings 2023-05-26 09:24:03 -04:00
Konstantin Gukov
6e3c59d8b2 reduce nesting, better error reporting 2023-05-26 09:24:03 -04:00
Konstantin Gukov
591a047204 Concise model matching 2023-05-26 09:24:03 -04:00
Konstantin Gukov
4de8f991f9 Log where the model was found 2023-05-26 09:24:03 -04:00
Konstantin Gukov
b6b21441c7 Nicer handling of missing model directory.
Correct exception message.
2023-05-26 09:24:03 -04:00
Konstantin Gukov
84201784b5 More precise condition 2023-05-26 09:24:03 -04:00
Konstantin Gukov
e3bdc8fc87 rm redundant json 2023-05-26 09:24:03 -04:00
Adam Treat
55b4f35510 This time remember to bump the version right after a release. 2023-05-25 18:26:33 -04:00
Adam Treat
c5c8ab9138 Bump the version number. 2023-05-25 17:08:50 -04:00
Adam Treat
4e8dba107f Libraries named differently on msvc. 2023-05-25 16:27:09 -04:00
Adam Treat
d40735a2d2 Get the backend as well as the client building/working with msvc. 2023-05-25 15:22:45 -04:00
redthing1
0e11584783 make sample print usage and cleaner 2023-05-25 11:34:21 -04:00
redthing1
448acb337d create test project and basic model loading tests 2023-05-25 11:34:07 -04:00
redthing1
9248bd0c1e ignore rider and vscode dirs 2023-05-25 11:34:07 -04:00
Adam Treat
ff51cb872f Add a newline 2023-05-25 11:28:06 -04:00
Adam Treat
580aceb2b3 Various fixes to remove unnecessary warnings. 2023-05-25 11:28:06 -04:00
Adam Treat
e6f5d88f17 Don't use the full path in reference text. 2023-05-25 11:28:06 -04:00
Adam Treat
0a4c3a14ca Add context link to references. 2023-05-25 11:28:06 -04:00
Adam Treat
f3dc031a9d Store the references separately so they are not sent to datalake. 2023-05-25 11:28:06 -04:00
Adam Treat
05c3edb387 Adds the collections to serialize and implement references for localdocs. 2023-05-25 11:28:06 -04:00
Adam Treat
90b2cf747f Complete the settings for localdocs. 2023-05-25 11:28:06 -04:00
Adam Treat
53cf2da5f7 Add more of the UI for selecting collections for chats. 2023-05-25 11:28:06 -04:00
Adam Treat
63c5911604 Clean up the settings dialog for localdocs a bit. 2023-05-25 11:28:06 -04:00
Adam Treat
1930070fdb Begin implementing the localdocs ui in earnest. 2023-05-25 11:28:06 -04:00
Adam Treat
695d1d048b Start fleshing out the localdocs ui. 2023-05-25 11:28:06 -04:00
Adam Treat
38c403dab8 Add a localdocs tab. 2023-05-25 11:28:06 -04:00
Adam Treat
32be0a92d7 Add a collection list to support a UI. 2023-05-25 11:28:06 -04:00
Adam Treat
e47f4ddfb6 Specify a large number of suffixes we will search for now. 2023-05-25 11:28:06 -04:00
Adam Treat
c33bf0e895 Add prompt processing and localdocs to the busy indicator in UI. 2023-05-25 11:28:06 -04:00
Adam Treat
837ece220f Turn off the debugging messages by default. 2023-05-25 11:28:06 -04:00
Adam Treat
90ab9183ae Add a new muted text color. 2023-05-25 11:28:06 -04:00
Adam Treat
80024a029c Add new reverse prompt for new localdocs context feature. 2023-05-25 11:28:06 -04:00