Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-26 17:50:22 +01:00
Code Issues Packages Projects Releases Wiki Activity
1,588 Commits 3 Branches 52 Tags 67 MiB
f54256e348
Commit Graph

1588 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
oobabooga
f54256e348 Rename no_mmap to no-mmap 2023-05-03 09:50:31 -03:00
oobabooga
875da16b7b Minor CSS improvements in chat mode 2023-05-02 23:38:51 -03:00
practicaldreamer
e3968f7dd0
Fix Training Pad Token (#1678) 
Currently padding with 0 the character vs 0 the token id (<unk> in the case of llama)
 2023-05-02 23:16:08 -03:00
Wojtab
80c2f25131
LLaVA: small fixes (#1664) 
* change multimodal projector to the correct one

* remove reference to custom stopping strings from readme

* fix stopping strings if tokenizer extension adds/removes tokens

* add API example

* LLaVA 7B just dropped, add to readme that there is no support for it currently
 2023-05-02 23:12:22 -03:00
oobabooga
c31b0f15a7 Remove some spaces 2023-05-02 23:07:07 -03:00
oobabooga
320fcfde4e Style/pep8 improvements 2023-05-02 23:05:38 -03:00
oobabooga
ecd79caa68
Update Extensions.md 2023-05-02 22:52:32 -03:00
matatonic
7ac41b87df
add openai compatible api (#1475) 2023-05-02 22:49:53 -03:00
oobabooga
4e09df4034 Only show extension in UI if it has an ui() function 2023-05-02 19:20:02 -03:00
oobabooga
d016c38640 Bump gradio version 2023-05-02 19:19:33 -03:00
oobabooga
88cdf6ed3d Prevent websocket from disconnecting 2023-05-02 19:03:19 -03:00
Ahmed Said
fbcd32988e
added no_mmap & mlock parameters to llama.cpp and removed llamacpp_model_alternative (#1649) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2023-05-02 18:25:28 -03:00
Carl Kenner
2f1a2846d1
Verbose should always print special tokens in input (#1707) 2023-05-02 01:24:56 -03:00
Alex "mcmonkey" Goodwin
0df0b2d0f9
optimize stopping strings processing (#1625) 2023-05-02 01:21:54 -03:00
oobabooga
e6a78c00f2
Update Docker.md 2023-05-02 00:51:10 -03:00
Tom Jobbins
3c67fc0362
Allow groupsize 1024, needed for larger models eg 30B to lower VRAM usage (#1660) 2023-05-02 00:46:26 -03:00
Lawrence M Stewart
78bd4d3a5c
Update LLaMA-model.md (#1700) 
protobuf needs to be 3.20.x or lower
 2023-05-02 00:44:09 -03:00
Dhaladom
f659415170
fixed variable name "context" to "prompt" (#1716) 2023-05-02 00:43:40 -03:00
dependabot[bot]
280c2f285f
Bump safetensors from 0.3.0 to 0.3.1 (#1720) 2023-05-02 00:42:39 -03:00
oobabooga
56b13d5d48 Bump llama-cpp-python version 2023-05-02 00:41:54 -03:00
Lőrinc Pap
ee68ec9079
Update folder produced by download-model (#1601) 2023-04-27 12:03:02 -03:00
oobabooga
91745f63c3 Use Vicuna-v0 by default for Vicuna models 2023-04-26 17:45:38 -03:00
oobabooga
93e5c066ae Update RWKV Raven template 2023-04-26 17:31:03 -03:00
oobabooga
c83210c460 Move the rstrips 2023-04-26 17:17:22 -03:00
oobabooga
1d8b8222e9 Revert #1579, apply the proper fix 
Apparently models dislike trailing spaces.
 2023-04-26 16:47:50 -03:00
TiagoGF
a941c19337
Fixing Vicuna text generation (#1579) 2023-04-26 16:20:27 -03:00
oobabooga
d87ca8f2af LLaVA fixes 2023-04-26 03:47:34 -03:00
oobabooga
9c2e7c0fab Fix path on models.py 2023-04-26 03:29:09 -03:00
oobabooga
a777c058af
Precise prompts for instruct mode 2023-04-26 03:21:53 -03:00
oobabooga
a8409426d7
Fix bug in models.py 2023-04-26 01:55:40 -03:00
oobabooga
4c491aa142 Add Alpaca prompt with Input field 2023-04-25 23:50:32 -03:00
oobabooga
68ed73dd89 Make API extension print its exceptions 2023-04-25 23:23:47 -03:00
oobabooga
f642135517 Make universal tokenizer, xformers, sdp-attention apply to monkey patch 2023-04-25 23:18:11 -03:00
oobabooga
f39c99fa14 Load more than one LoRA with --lora, fix a bug 2023-04-25 22:58:48 -03:00
oobabooga
15940e762e Fix missing initial space for LlamaTokenizer 2023-04-25 22:47:23 -03:00
Vincent Brouwers
92cdb4f22b
Seq2Seq support (including FLAN-T5) (#1535) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2023-04-25 22:39:04 -03:00
USBhost
95aa43b9c2
Update LLaMA download docs 2023-04-25 21:28:15 -03:00
Alex "mcmonkey" Goodwin
312cb7dda6
LoRA trainer improvements part 5 (#1546) 
* full dynamic model type support on modern peft

* remove shuffle option
 2023-04-25 21:27:30 -03:00
Wojtab
65beb51b0b
fix returned dtypes for LLaVA (#1547) 2023-04-25 21:25:34 -03:00
oobabooga
9b272bc8e5 Monkey patch fixes 2023-04-25 21:20:26 -03:00
oobabooga
da812600f4 Apply settings regardless of setup() function 2023-04-25 01:16:23 -03:00
da3dsoul
ebca3f86d5
Apply the settings for extensions after import, but before setup() (#1484) 2023-04-25 00:23:11 -03:00
oobabooga
b0ce750d4e Add spaces 2023-04-25 00:10:21 -03:00
oobabooga
1a0c12c6f2
Refactor text-generation.py a bit 2023-04-24 19:24:12 -03:00
oobabooga
2f4f124132 Remove obsolete function 2023-04-24 13:27:24 -03:00
oobabooga
b6af2e56a2 Add --character flag, add character to settings.json 2023-04-24 13:19:42 -03:00
oobabooga
0c32ae27cc Only load the default history if it's empty 2023-04-24 11:50:51 -03:00
MajdajkD
c86e9a3372
fix websocket batching (#1511) 2023-04-24 03:51:32 -03:00
eiery
78d1977ebf
add n_batch support for llama.cpp (#1115) 2023-04-24 03:46:18 -03:00
oobabooga
2f6e2ddeac Bump llama-cpp-python version 2023-04-24 03:42:03 -03:00