anon
|
41bb71bde7
|
replace invalid characters instead of crashing
While logging the requests.
|
2023-06-02 10:37:13 -03:00 |
|
digiwombat
|
3ff27d30e3
|
Fixed up a few things in embedding mode.
|
2023-06-02 09:20:53 -04:00 |
|
Randall Fitzgerald
|
28cc0cdc50
|
Merge pull request #15 from SlyEcho/server_refactor
Improve long input truncation and add more verbose logging
|
2023-06-02 08:47:54 -04:00 |
|
Henri Vasserman
|
3df0192804
|
improve long input truncation
and add more verbose logging
|
2023-06-02 15:19:05 +03:00 |
|
Randall Fitzgerald
|
1bd52c8627
|
Merge branch 'ggerganov:master' into master
|
2023-06-02 07:31:55 -04:00 |
|
Randall Fitzgerald
|
f5d5e7020d
|
Merge pull request #14 from anon998/do-completion-update
Trim partial stopping strings when not streaming and move multibyte check.
|
2023-06-02 07:30:53 -04:00 |
|
anon
|
f820740dad
|
move multibyte check to doCompletion
|
2023-06-02 08:27:23 -03:00 |
|
anon
|
8f9e546b51
|
trim partial stopping strings when not streaming
|
2023-06-02 08:25:31 -03:00 |
|
Randall Fitzgerald
|
bebea657cb
|
Merge pull request #13 from anon998/small-fixes
Small fixes.
|
2023-06-02 06:53:10 -04:00 |
|
anon998
|
abb7782745
|
Merge branch 'master' into small-fixes
|
2023-06-02 10:35:06 +00:00 |
|
Henri Vasserman
|
88cc7bb6f7
|
Stuff with logits
|
2023-06-02 13:29:57 +03:00 |
|
anon
|
47efbb5cf3
|
use std::isinf to check if ignore_eos is active
|
2023-06-02 07:19:21 -03:00 |
|
anon
|
2932db15a3
|
avoid creating element in logit_bias accidentally
|
2023-06-02 06:59:11 -03:00 |
|
anon
|
a8a9f19689
|
small fixes
|
2023-06-02 06:01:10 -03:00 |
|
anon
|
49dce94885
|
make types match gpt_params exactly
|
2023-06-02 06:01:10 -03:00 |
|
anon
|
1488a0f528
|
make functions that never return false void
|
2023-06-02 06:00:48 -03:00 |
|
anon
|
ebfead6e5a
|
remove unused variables
|
2023-06-02 05:45:57 -03:00 |
|
anon
|
731ecc0d1b
|
fix typo
|
2023-06-02 05:45:16 -03:00 |
|
Henri Vasserman
|
0bc047730f
|
Apply suggestions from code review
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
|
2023-06-02 10:29:09 +03:00 |
|
Randall Fitzgerald
|
d29b6d5f55
|
Merge pull request #12 from anon998/clear-logit-bias
Clear logit bias between requests.
|
2023-06-01 08:58:35 -04:00 |
|
anon
|
8cbc4be6c2
|
clear logit_bias between requests + print
|
2023-06-01 09:49:50 -03:00 |
|
anon
|
6025476e39
|
default penalize_nl back to true
|
2023-06-01 09:49:16 -03:00 |
|
anon
|
49a18bdd14
|
remove unused parameter warning
|
2023-06-01 09:41:35 -03:00 |
|
Randall Fitzgerald
|
af711263ae
|
Merge pull request #11 from SlyEcho/server_refactor
Server refactor
|
2023-06-01 08:10:55 -04:00 |
|
Randall Fitzgerald
|
797155a0d1
|
Merge pull request #10 from cirk2/master
Add Options enpoints and Access-Control-Allow-Headers to satisfy CORS
|
2023-06-01 08:10:26 -04:00 |
|
Henri Vasserman
|
9531ae60db
|
Add logit bias support
|
2023-06-01 13:57:47 +03:00 |
|
Henri Vasserman
|
8c6a5fc92b
|
last tokens fixes
|
2023-06-01 13:18:12 +03:00 |
|
Felix Hellmann
|
5bbc030338
|
Add Options enpoints and Access-Control-Allow-Headers to satisfy CORS rules
|
2023-06-01 10:47:53 +02:00 |
|
digiwombat
|
f7882e2d69
|
Fixed a crash caused by erasing from empty last_n_tokens
|
2023-05-31 20:35:28 -04:00 |
|
Randall Fitzgerald
|
5f6e16da36
|
Merge pull request #9 from anon998/stopping-strings
Fix stopping strings.
|
2023-05-31 20:05:18 -04:00 |
|
anon
|
e9b1f0bf5c
|
fix stopping strings
|
2023-05-31 21:00:21 -03:00 |
|
digiwombat
|
342604bb81
|
Added a super simple CORS header as default for all endpoints.
|
2023-05-31 19:54:05 -04:00 |
|
Henri Vasserman
|
bed308c69c
|
Apply suggestions from code review
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
|
2023-06-01 01:15:48 +03:00 |
|
Randall Fitzgerald
|
8478e59b08
|
Merge pull request #8 from SlyEcho/server_refactor
Change how the token buffers work.
|
2023-05-31 18:03:40 -04:00 |
|
Henri Vasserman
|
9104fe5a7c
|
Change how the token buffers work.
There is now just embd (and last_n_tokens).
The input can also be of any length in which case it will be truncated
like it normally would.
|
2023-06-01 00:47:11 +03:00 |
|
Randall Fitzgerald
|
f2e1130901
|
Merge pull request #7 from anon998/logging-reuse
Reuse format_generation_settings for logging.
|
2023-05-31 17:08:12 -04:00 |
|
anon
|
497160a60d
|
remove old log function
|
2023-05-31 18:01:07 -03:00 |
|
anon
|
1bd7cc60a8
|
reuse format_generation_settings for logging
|
2023-05-31 18:00:07 -03:00 |
|
anon
|
43d295fddc
|
filter empty stopping strings
|
2023-05-31 18:00:07 -03:00 |
|
digiwombat
|
276fa99873
|
Misunderstood the instructions, I think. Back to the raw JSON output only.
|
2023-05-31 16:45:57 -04:00 |
|
digiwombat
|
1b96df2b5f
|
Spacing fix. Nothing to see here.
|
2023-05-31 16:42:43 -04:00 |
|
digiwombat
|
86337e3a9b
|
Server console logs now come in one flavor: Verbose.
|
2023-05-31 16:41:34 -04:00 |
|
digiwombat
|
dda4c10d64
|
Switch to the CPPHTTPLIB logger. Verbose adds body dump as well as request info.
|
2023-05-31 16:23:39 -04:00 |
|
digiwombat
|
7332b41f9f
|
Simple single-line server log for requests
|
2023-05-31 15:56:27 -04:00 |
|
Randall Fitzgerald
|
96fa480147
|
Merge pull request #6 from anon998/fix-multibyte
Buffer incomplete multibyte characters + other stuff.
|
2023-05-31 12:14:43 -04:00 |
|
anon
|
3edaf6bd8b
|
print timings by default
|
2023-05-31 12:55:19 -03:00 |
|
anon
|
d58e48663d
|
default penalize_nl to false + format
|
2023-05-31 12:44:27 -03:00 |
|
anon
|
40e13805d9
|
print timings + build info
I don't know if llama_free is needed but it was used in main.cpp.
|
2023-05-31 12:44:24 -03:00 |
|
anon
|
dd30219332
|
buffer incomplete multi-byte characters
|
2023-05-31 12:31:27 -03:00 |
|
anon
|
27911d6d68
|
fix default model alias
|
2023-05-31 12:31:25 -03:00 |
|