Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-12-25 22:08:53 +01:00
Code Issues Packages Projects Releases Wiki Activity
2,104 Commits 7 Branches 53 Tags 70 MiB
ff45317032
Commit Graph

718 Commits

Author SHA1 Message Date
sgsdxzy
b57ffc2ec9
Update to support GPTQ triton commit c90adef (#1229) 2023-04-17 01:11:18 -03:00
oobabooga
39099663a0
Add 4-bit LoRA support (#1200) 2023-04-16 23:26:52 -03:00
oobabooga
46a8aa8c09 Readability 2023-04-16 21:26:19 -03:00
Forkoz
c6fe1ced01
Add ChatGLM support (#1256) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2023-04-16 19:15:03 -03:00
oobabooga
6a03ad0824 Remove fix_newlines() calls from chat.py 2023-04-16 18:25:44 -03:00
oobabooga
5342f72968 Properly handle blockquote blocks 2023-04-16 18:00:12 -03:00
oobabooga
27f3a78834 Better detect when no model is loaded 2023-04-16 17:35:54 -03:00
oobabooga
c8ad960018 Add defaults to the gradio API 2023-04-16 17:33:28 -03:00
oobabooga
beb95f5fe2 Add a style for the "chat" mode 2023-04-16 16:44:50 -03:00
oobabooga
b937c9d8c2
Add skip_special_tokens checkbox for Dolly model (#1218) 2023-04-16 14:24:49 -03:00
oobabooga
b705b4210c Minor changes to training.py 2023-04-16 03:08:37 -03:00
oobabooga
5c513a5f5c Make training.py more readable 2023-04-16 02:46:27 -03:00
Alex "mcmonkey" Goodwin
a3eec62b50
Lora trainer improvements part 3 (#1098) 
* add support for other model types

dependent on future-peft-changes but with fallback to function now

* use encoding=utf8 for training format

* make shuffling optional

and describe dropout a bit more

* add eval_steps to control evaluation

* make callbacks not depend on globals

* make save steps controllable

* placeholder of initial loading-existing-model support

and var name cleanup

* save/load parameters

* last bit of cleanup

* remove `gptq_bits` ref as main branch removed that setting

* add higher_rank_limit option

2048 is basically unreachable due to VRAM, but i trained at 1536 with batch size = 1 on a 7B model.
Note that it's in the do_train input just to save as a parameter

* fix math on save_steps
 2023-04-16 02:35:13 -03:00
kernyan
ac19d5101f
revert incorrect eos_token_id change from #814 (#1261) 
- fixes #1054
 2023-04-16 01:47:01 -03:00
oobabooga
a2127239de Fix a bug 2023-04-16 01:41:37 -03:00
oobabooga
9d3c6d2dc3 Fix a bug 2023-04-16 01:40:47 -03:00
Mikel Bober-Irizar
16a3a5b039
Merge pull request from GHSA-hv5m-3rp9-xcpf 
* Remove eval of API input

* Remove unnecessary eval/exec for security

* Use ast.literal_eval

* Use ast.literal_eval

---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2023-04-16 01:36:50 -03:00
oobabooga
d2ea925fa5 Bump llama-cpp-python to use LlamaCache 2023-04-16 00:53:40 -03:00
oobabooga
ac189011cb Add "Save current settings for this model" button 2023-04-15 12:54:02 -03:00
oobabooga
abef355ed0 Remove deprecated flag 2023-04-15 01:21:19 -03:00
oobabooga
c3aa79118e Minor generate_chat_prompt simplification 2023-04-14 23:02:08 -03:00
oobabooga
3a337cfded Use argparse defaults 2023-04-14 15:35:06 -03:00
Alex "mcmonkey" Goodwin
64e3b44e0f
initial multi-lora support (#1103) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2023-04-14 14:52:06 -03:00
oobabooga
1901d238e1 Minor change to API code 2023-04-14 12:11:47 -03:00
oobabooga
8e31f2bad4
Automatically set wbits/groupsize/instruct based on model name (#1167) 2023-04-14 11:07:28 -03:00
v0xie
9d66957207
Add --listen-host launch option (#1122) 2023-04-13 21:35:08 -03:00
oobabooga
a75e02de4d Simplify GPTQ_loader.py 2023-04-13 12:13:07 -03:00
oobabooga
ca293bb713 Show a warning if two quantized models are found 2023-04-13 12:04:27 -03:00
oobabooga
8b482b4127
Merge #1073 from sgsdxzy/triton 
* Multi-GPU support for triton
* Better quantized model filename detection
 2023-04-13 11:31:21 -03:00
oobabooga
fde6d06167 Prioritize names with the groupsize in them 2023-04-13 11:27:03 -03:00
oobabooga
f2bf1a2c9e Add some comments, remove obsolete code 2023-04-13 11:17:32 -03:00
Light
da74cd7c44 Generalized weight search path. 2023-04-13 21:43:32 +08:00
oobabooga
04866dc4fc Add a warning for when no model is loaded 2023-04-13 10:35:08 -03:00
Light
cf58058c33 Change warmup_autotune to a negative switch. 2023-04-13 20:59:49 +08:00
Light
15d5a043f2 Merge remote-tracking branch 'origin/main' into triton 2023-04-13 19:38:51 +08:00
oobabooga
7dfbe54f42 Add --model-menu option 2023-04-12 21:24:26 -03:00
oobabooga
388038fb8e Update settings-template.json 2023-04-12 18:30:43 -03:00
oobabooga
10e939c9b4 Merge branch 'main' of github.com:oobabooga/text-generation-webui 2023-04-12 17:21:59 -03:00
oobabooga
1566d8e344 Add model settings to the Models tab 2023-04-12 17:20:18 -03:00
Light
a405064ceb Better dispatch. 2023-04-13 01:48:17 +08:00
Light
f3591ccfa1 Keep minimal change. 2023-04-12 23:26:06 +08:00
Lukas
5ad92c940e
lora training fixes: (#970) 
Fix wrong input format being picked
Fix crash when an entry in the dataset has an attribute of value None
 2023-04-12 11:38:01 -03:00
oobabooga
80f4eabb2a Fix send_pictures extension 2023-04-12 10:27:06 -03:00
oobabooga
8265d45db8 Add send dummy message/reply buttons 
Useful for starting a new reply.
 2023-04-11 22:21:41 -03:00
oobabooga
37d52c96bc Fix Continue in chat mode 2023-04-11 21:46:17 -03:00
oobabooga
cacbcda208
Two new options: truncation length and ban eos token 2023-04-11 18:46:06 -03:00
catalpaaa
78bbc66fc4
allow custom stopping strings in all modes (#903) 2023-04-11 12:30:06 -03:00
oobabooga
0f212093a3
Refactor the UI 
A single dictionary called 'interface_state' is now passed as input to all functions. The values are updated only when necessary.

The goal is to make it easier to add new elements to the UI.
 2023-04-11 11:46:30 -03:00
IggoOnCode
09d8119e3c
Add CPU LoRA training (#938) 
(It's very slow)
 2023-04-10 17:29:00 -03:00
Alex "mcmonkey" Goodwin
0caf718a21
add on-page documentation to parameters (#1008) 2023-04-10 17:19:12 -03:00
oobabooga
bd04ff27ad Make the bos token optional 2023-04-10 16:44:22 -03:00
oobabooga
0f1627eff1 Don't treat Intruct mode histories as regular histories 
* They must now be saved/loaded manually
* Also improved browser caching of pfps
* Also changed the global default preset
 2023-04-10 15:48:07 -03:00
oobabooga
769aa900ea Print the used seed 2023-04-10 10:53:31 -03:00
Alex "mcmonkey" Goodwin
30befe492a fix random seeds to actually randomize 
Without this fix, manual seeds get locked in.
 2023-04-10 06:29:10 -07:00
oobabooga
1911504f82 Minor bug fix 2023-04-09 23:45:41 -03:00
oobabooga
dba2000d2b Do things that I am not proud of 2023-04-09 23:40:49 -03:00
oobabooga
65552d2157 Merge branch 'main' of github.com:oobabooga/text-generation-webui 2023-04-09 23:19:53 -03:00
oobabooga
8c6155251a More robust 4-bit model loading 2023-04-09 23:19:28 -03:00
MarkovInequality
992663fa20
Added xformers support to Llama (#950) 2023-04-09 23:08:40 -03:00
Brian O'Connor
625d81f495
Update character log logic (#977) 
* When logs are cleared, save the cleared log over the old log files
* Generate a log file when a character is loaded the first time
 2023-04-09 22:20:21 -03:00
oobabooga
a3085dba07 Fix LlamaTokenizer eos_token (attempt) 2023-04-09 21:19:39 -03:00
oobabooga
120f5662cf Better handle spaces for Continue 2023-04-09 20:37:31 -03:00
oobabooga
b27d757fd1 Minor change 2023-04-09 20:06:20 -03:00
oobabooga
d29f4624e9 Add a Continue button to chat mode 2023-04-09 20:04:16 -03:00
oobabooga
cc693a7546 Remove obsolete code 2023-04-09 00:51:07 -03:00
oobabooga
cb169d0834 Minor formatting changes 2023-04-08 17:34:07 -03:00
oobabooga
0b458bf82d Simplify a function 2023-04-07 21:37:41 -03:00
Φφ
ffd102e5c0
SD Api Pics extension, v.1.1 (#596) 2023-04-07 21:36:04 -03:00
oobabooga
1dc464dcb0 Sort imports 2023-04-07 14:42:03 -03:00
oobabooga
42ea6a3fc0 Change the timing for setup() calls 2023-04-07 12:20:57 -03:00
oobabooga
768354239b Change training file encoding 2023-04-07 11:15:52 -03:00
oobabooga
6762e62a40 Simplifications 2023-04-07 11:14:32 -03:00
oobabooga
a453d4e9c4 Reorganize some chat functions 2023-04-07 11:07:03 -03:00
Maya
8fa182cfa7
Fix regeneration of first message in instruct mode (#881) 2023-04-07 10:45:42 -03:00
oobabooga
46c4654226 More PEP8 stuff 2023-04-07 00:52:02 -03:00
oobabooga
ea6e77df72
Make the code more like PEP8 for readability (#862) 2023-04-07 00:15:45 -03:00
OWKenobi
310bf46a94
Instruction Character Vicuna, Instruction Mode Bugfix (#838) 2023-04-06 17:40:44 -03:00
oobabooga
113f94b61e Bump transformers (16-bit llama must be reconverted/redownloaded) 2023-04-06 16:04:03 -03:00
oobabooga
03cb44fc8c Add new llama.cpp library (2048 context, temperature, etc now work) 2023-04-06 13:12:14 -03:00
EyeDeck
39f3fec913
Broaden GPTQ-for-LLaMA branch support (#820) 2023-04-06 12:16:48 -03:00
Alex "mcmonkey" Goodwin
0c7ef26981
Lora trainer improvements (#763) 2023-04-06 02:04:11 -03:00
oobabooga
e94ab5dac1 Minor fixes 2023-04-06 01:43:10 -03:00
oobabooga
3f3e42e26c
Refactor several function calls and the API 2023-04-06 01:22:15 -03:00
SDS
378d21e80c
Add LLaMA-Precise preset (#767) 2023-04-05 18:52:36 -03:00
Forkoz
8203ce0cac
Stop character pic from being cached when changing chars or clearing. (#798) 
Tested on both FF and chromium
 2023-04-05 14:25:01 -03:00
oobabooga
7f66421369 Fix loading characters 2023-04-05 14:22:32 -03:00
oobabooga
e722c240af Add Instruct mode 2023-04-05 13:54:50 -03:00
oobabooga
3d6cb5ed63 Minor rewrite 2023-04-05 01:21:40 -03:00
oobabooga
f3a2e0b8a9 Disable pre_layer when the model type is not llama 2023-04-05 01:19:26 -03:00
catalpaaa
4ab679480e
allow quantized model to be loaded from model dir (#760) 2023-04-04 23:19:38 -03:00
oobabooga
ae1fe45bc0 One more cache reset 2023-04-04 23:15:57 -03:00
oobabooga
8ef89730a5 Try to better handle browser image cache 2023-04-04 23:09:28 -03:00
oobabooga
cc6c7a37f3 Add make_thumbnail function 2023-04-04 23:03:58 -03:00
oobabooga
80dfba05f3 Better crop/resize cached images 2023-04-04 22:52:15 -03:00
oobabooga
65d8a24a6d Show profile pictures in the Character tab 2023-04-04 22:28:49 -03:00
OWKenobi
ee4547cd34
Detect "vicuna" as llama model type (#772) 2023-04-04 13:23:27 -03:00
oobabooga
b24147c7ca Document --pre_layer 2023-04-03 17:34:25 -03:00
oobabooga
4c9ed09270 Update settings template 2023-04-03 14:59:26 -03:00
OWKenobi
dcf61a8897
"character greeting" displayed and editable on the fly (#743) 
* Add greetings field

* add greeting field and make it interactive

* Minor changes

* Fix a bug

* Simplify clear_chat_log

* Change a label

* Minor change

* Simplifications

* Simplification

* Simplify loading the default character history

* Fix regression

---------

Co-authored-by: oobabooga
 2023-04-03 12:16:15 -03:00
Alex "mcmonkey" Goodwin
8b1f20aa04
Fix some old JSON characters not loading (#740) 2023-04-03 10:49:28 -03:00
oobabooga
8b442305ac Rename another variable 2023-04-03 01:15:20 -03:00
oobabooga
08448fb637 Rename a variable 2023-04-03 01:02:11 -03:00
oobabooga
2a267011dc Use Path.stem for simplicity 2023-04-03 00:56:14 -03:00
Alex "mcmonkey" Goodwin
ea97303509
Apply dialogue format in all character fields not just example dialogue (#650) 2023-04-02 21:54:29 -03:00
TheTerrasque
2157bb4319
New yaml character format (#337 from TheTerrasque/feature/yaml-characters) 
This doesn't break backward compatibility with JSON characters.
 2023-04-02 20:34:25 -03:00
oobabooga
5f3f3faa96 Better handle CUDA out of memory errors in chat mode 2023-04-02 17:48:00 -03:00
oobabooga
b0890a7925 Add shared.is_chat() function 2023-04-01 20:15:00 -03:00
oobabooga
b857f4655b
Update shared.py 2023-04-01 13:56:47 -03:00
oobabooga
fcda3f8776 Add also_return_rows to generate_chat_prompt 2023-04-01 01:12:13 -03:00
oobabooga
2c52310642 Add --threads flag for llama.cpp 2023-03-31 21:18:05 -03:00
oobabooga
eeafd60713 Fix streaming 2023-03-31 19:05:38 -03:00
oobabooga
52065ae4cd Add repetition_penalty 2023-03-31 19:01:34 -03:00
oobabooga
2259143fec Fix llama.cpp with --no-stream 2023-03-31 18:43:45 -03:00
oobabooga
3a47a602a3 Detect ggml*.bin files automatically 2023-03-31 17:18:21 -03:00
oobabooga
0aee7341d8 Properly count tokens/s for llama.cpp in chat mode 2023-03-31 17:04:32 -03:00
oobabooga
ea3ba6fc73 Merge branch 'feature/llamacpp' of github.com:thomasantony/text-generation-webui into thomasantony-feature/llamacpp 2023-03-31 14:45:53 -03:00
oobabooga
09b0a3aafb Add repetition_penalty 2023-03-31 14:45:17 -03:00
oobabooga
4d98623041
Merge branch 'main' into feature/llamacpp 2023-03-31 14:37:04 -03:00
oobabooga
4c27562157 Minor changes 2023-03-31 14:33:46 -03:00
oobabooga
9d1dcf880a General improvements 2023-03-31 14:27:01 -03:00
oobabooga
770ff0efa9 Merge branch 'main' of github.com:oobabooga/text-generation-webui 2023-03-31 12:22:22 -03:00
oobabooga
1d1d9e40cd Add seed to settings 2023-03-31 12:22:07 -03:00
Maya
b246d17513
Fix type object is not subscriptable 
Fix `type object is not subscriptable` on python 3.8
 2023-03-31 14:20:31 +03:00
oobabooga
d4a9b5ea97 Remove redundant preset (see the plot in #587) 2023-03-30 17:34:44 -03:00
Thomas Antony
7fa5d96c22 Update to use new llamacpp API 2023-03-30 11:23:05 +01:00
Thomas Antony
79fa2b6d7e Add support for alpaca 2023-03-30 11:23:04 +01:00
Thomas Antony
a5f5736e74 Add to text_generation.py 2023-03-30 11:22:38 +01:00
Thomas Antony
7745faa7bb Add llamacpp to models.py 2023-03-30 11:22:37 +01:00
Thomas Antony
7a562481fa Initial version of llamacpp_model.py 2023-03-30 11:22:07 +01:00
oobabooga
a21e580782 Move an import 2023-03-29 22:50:58 -03:00
oobabooga
55755e27b9 Don't hardcode prompts in the settings dict/json 2023-03-29 22:47:01 -03:00
oobabooga
1cb9246160 Adapt to the new model names 2023-03-29 21:47:36 -03:00
oobabooga
58349f44a0
Handle training exception for unsupported models 2023-03-29 11:55:34 -03:00
oobabooga
a6d0373063
Fix training dataset loading #636 2023-03-29 11:48:17 -03:00
oobabooga
1edfb96778
Fix loading extensions from within the interface 2023-03-28 23:27:02 -03:00
oobabooga
304f812c63 Gracefully handle CUDA out of memory errors with streaming 2023-03-28 19:20:50 -03:00
oobabooga
010b259dde Update documentation 2023-03-28 17:46:00 -03:00
oobabooga
0bec15ebcd Reorder imports 2023-03-28 17:34:15 -03:00
Maya Eary
41ec682834 Disable kernel threshold for gpt-j 2023-03-28 22:45:38 +03:00
Maya
1ac003d41c
Merge branch 'oobabooga:main' into feature/gpt-j-4bit-v2 2023-03-28 22:30:39 +03:00
Maya Eary
1c075d8d21 Fix typo 2023-03-28 20:43:50 +03:00
Maya Eary
c8207d474f Generalized load_quantized 2023-03-28 20:38:55 +03:00
oobabooga
8579fe51dd Fix new lines in the HTML tab 2023-03-28 12:59:34 -03:00
Alex "mcmonkey" Goodwin
e817fac542 better defaults 2023-03-27 22:29:23 -07:00
Alex "mcmonkey" Goodwin
2e08af4edf implement initial Raw Text File Input 
also bump default Rank & Alpha for values that will make sense in testing if you don't know what you're doing and leave the defaults.
 2023-03-27 22:15:32 -07:00
Alex "mcmonkey" Goodwin
b749952fe3 change number minimums to 0 
gradio calculates 'step' relative to the minimum, so at '1' the step values were all offset awkwardly. 0 isn't valid, but, uh, just don't slam the slider to the left.
 2023-03-27 21:22:43 -07:00
Alex "mcmonkey" Goodwin
ec6224f556 use new shared.args.lora_dir 2023-03-27 20:04:16 -07:00
Alex "mcmonkey" Goodwin
31f04dc615 Merge branch 'main' into add-train-lora-tab 2023-03-27 20:03:30 -07:00
oobabooga
53da672315 Fix FlexGen 2023-03-27 23:44:21 -03:00
oobabooga
ee95e55df6 Fix RWKV tokenizer 2023-03-27 23:42:29 -03:00
oobabooga
036163a751 Change description 2023-03-27 23:39:26 -03:00
oobabooga
005f552ea3 Some simplifications 2023-03-27 23:29:52 -03:00
oobabooga
fde92048af Merge branch 'main' into catalpaaa-lora-and-model-dir 2023-03-27 23:16:44 -03:00
Alex "mcmonkey" Goodwin
8a97f6ba29 corrections per the PR comments 2023-03-27 18:39:06 -07:00
Alex "mcmonkey" Goodwin
7fab7ea1b6 couple missed camelCases 2023-03-27 18:19:06 -07:00
Alex "mcmonkey" Goodwin
6368dad7db Fix camelCase to snake_case to match repo format standard 2023-03-27 18:17:42 -07:00
oobabooga
2f0571bfa4 Small style changes 2023-03-27 21:24:39 -03:00
oobabooga
c2cad30772 Merge branch 'main' into mcmonkey4eva-add-train-lora-tab 2023-03-27 21:05:44 -03:00
Alex "mcmonkey" Goodwin
9ced75746d add total time estimate 2023-03-27 10:57:27 -07:00
Alex "mcmonkey" Goodwin
16ea4fc36d interrupt button 2023-03-27 10:43:01 -07:00
Alex "mcmonkey" Goodwin
8fc723fc95 initial progress tracker in UI 2023-03-27 10:25:08 -07:00
oobabooga
48a6c9513e
Merge pull request #572 from clusterfudge/issues/571 
Potential fix for issues/571
 2023-03-27 14:06:38 -03:00
Alex "mcmonkey" Goodwin
c07bcd0850 add some outputs to indicate progress updates (sorta) 
Actual progressbar still needed. Also minor formatting fixes.
 2023-03-27 09:41:06 -07:00
oobabooga
af65c12900 Change Stop button behavior 2023-03-27 13:23:59 -03:00
Alex "mcmonkey" Goodwin
d911c22af9 use shared rows to make the LoRA Trainer interface a bit more compact / clean 2023-03-27 08:31:49 -07:00
Alex "mcmonkey" Goodwin
e439228ed8 Merge branch 'main' into add-train-lora-tab 2023-03-27 08:21:19 -07:00
oobabooga
3dc61284d5 Handle unloading LoRA from dropdown menu icon 2023-03-27 00:04:43 -03:00
oobabooga
1c77fdca4c Change notebook mode appearance 2023-03-26 22:20:30 -03:00
oobabooga
49c10c5570
Add support for the latest GPTQ models with group-size (#530) 
**Warning: old 4-bit weights will not work anymore!**

See here how to get up to date weights: https://github.com/oobabooga/text-generation-webui/wiki/LLaMA-model#step-2-get-the-pre-converted-weights
 2023-03-26 00:11:33 -03:00
Sean Fitzgerald
0bac80d9eb Potential fix for issues/571 2023-03-25 13:08:45 -07:00
Alex "mcmonkey" Goodwin
f1ba2196b1 make 'model' variables less ambiguous 2023-03-25 12:57:36 -07:00
Alex "mcmonkey" Goodwin
8da237223e document options better 2023-03-25 12:48:35 -07:00
Alex "mcmonkey" Goodwin
5c49a0dcd0 fix error from prepare call running twice in a row 2023-03-25 12:37:32 -07:00
Alex "mcmonkey" Goodwin
7bf601107c automatically strip empty data entries (for better alpaca dataset compat) 2023-03-25 12:28:46 -07:00
Alex "mcmonkey" Goodwin
566898a79a initial lora training tab 2023-03-25 12:08:26 -07:00
oobabooga
8c8e8b4450
Fix the early stopping callback #559 2023-03-25 12:35:52 -03:00
oobabooga
a1f12d607f
Merge pull request #538 from Ph0rk0z/display-input-context 
Add display of context when input was generated
 2023-03-25 11:56:18 -03:00
catalpaaa
f740ee558c
Merge branch 'oobabooga:main' into lora-and-model-dir 2023-03-25 01:28:33 -07:00
oobabooga
25be9698c7
Fix LoRA on mps 2023-03-25 01:18:32 -03:00
oobabooga
3da633a497
Merge pull request #529 from EyeDeck/main 
Allow loading of .safetensors through GPTQ-for-LLaMa
 2023-03-24 23:51:01 -03:00
catalpaaa
b37c54edcf lora-dir, model-dir and login auth 
Added lora-dir, model-dir, and a login auth arguments that points to a file contains usernames and passwords in the format of "u:pw,u:pw,..."
 2023-03-24 17:30:18 -07:00
oobabooga
9fa47c0eed
Revert GPTQ_loader.py (accident) 2023-03-24 19:57:12 -03:00
oobabooga
a6bf54739c
Revert models.py (accident) 2023-03-24 19:56:45 -03:00
oobabooga
0a16224451
Update GPTQ_loader.py 2023-03-24 19:54:36 -03:00
oobabooga
a80aa65986
Update models.py 2023-03-24 19:53:20 -03:00
oobabooga
507db0929d
Do not use empty user messages in chat mode 
This allows the bot to send messages by clicking on Generate with empty inputs.
 2023-03-24 17:22:22 -03:00
oobabooga
6e1b16c2aa
Update html_generator.py 2023-03-24 17:18:27 -03:00
oobabooga
ffb0187e83
Update chat.py 2023-03-24 17:17:29 -03:00
oobabooga
bfe960731f
Merge branch 'main' into fix/api-reload 2023-03-24 16:54:41 -03:00
oobabooga
8fad84abc2
Update extensions.py 2023-03-24 16:51:27 -03:00
Forkoz
b740c5b284
Add display of context when input was generated 
Not sure if I did this right but it does move with the conversation and seems to match value.
 2023-03-24 08:56:07 -05:00
oobabooga
4f5c2ce785
Fix chat_generation_attempts 2023-03-24 02:03:30 -03:00
EyeDeck
dcfd866402 Allow loading of .safetensors through GPTQ-for-LLaMa 2023-03-23 21:31:34 -04:00
oobabooga
8747c74339
Another missing import 2023-03-23 22:19:01 -03:00
oobabooga
7078d168c3
Missing import 2023-03-23 22:16:08 -03:00
oobabooga
d1327f99f9
Fix broken callbacks.py 2023-03-23 22:12:24 -03:00
oobabooga
b0abb327d8
Update LoRA.py 2023-03-23 22:02:09 -03:00
oobabooga
bf22d16ebc
Clear cache while switching LoRAs 2023-03-23 21:56:26 -03:00
oobabooga
4578e88ffd
Stop the bot from talking for you in chat mode 2023-03-23 21:38:20 -03:00
oobabooga
9bf6ecf9e2
Fix LoRA device map (attempt) 2023-03-23 16:49:41 -03:00
oobabooga
c5ebcc5f7e
Change the default names (#518) 
* Update shared.py

* Update settings-template.json
 2023-03-23 13:36:00 -03:00
oobabooga
29bd41d453
Fix LoRA in CPU mode 2023-03-23 01:05:13 -03:00
oobabooga
eac27f4f55
Make LoRAs work in 16-bit mode 2023-03-23 00:55:33 -03:00
oobabooga
bfa81e105e
Fix FlexGen streaming 2023-03-23 00:22:14 -03:00
oobabooga
de6a09dc7f
Properly separate the original prompt from the reply 2023-03-23 00:12:40 -03:00
wywywywy
61346b88ea
Add "seed" menu in the Parameters tab 2023-03-22 15:40:20 -03:00
oobabooga
45b7e53565
Only catch proper Exceptions in the text generation function 2023-03-20 20:36:02 -03:00
oobabooga
db4219a340
Update comments 2023-03-20 16:40:08 -03:00
oobabooga
7618f3fe8c
Add -gptq-preload for 4-bit offloading (#460) 
This works in a 4GB card now:

```
python server.py --model llama-7b-hf --gptq-bits 4 --gptq-pre-layer 20
```
 2023-03-20 16:30:56 -03:00
Vladimir Belitskiy
e96687b1d6 Do not send empty user input as part of the prompt. 
However, if extensions modify the empty prompt to be non-empty,
it'l still work as before.
 2023-03-20 14:27:39 -04:00
oobabooga
9a3bed50c3
Attempt at fixing 4-bit with CPU offload 2023-03-20 15:11:56 -03:00
Vladimir Belitskiy
ca47e016b4
Do not display empty user messages in chat mode. 
There doesn't seem to be much value to them - they just take up space while also making it seem like there's still some sort of pseudo-dialogue going on, instead of a monologue by the bot.
 2023-03-20 12:55:57 -04:00
oobabooga
75a7a84ef2
Exception handling (#454) 
* Update text_generation.py
* Update extensions.py
 2023-03-20 13:36:52 -03:00
oobabooga
ddb62470e9 --no-cache and --gpu-memory in MiB for fine VRAM control 2023-03-19 19:21:41 -03:00
oobabooga
a78b6508fc Make custom LoRAs work by default #385 2023-03-19 12:11:35 -03:00
Maya
acdbd6b708 Check if app should display extensions ui 2023-03-19 13:31:21 +00:00
Maya
81c9d130f2 Fix global 2023-03-19 13:25:49 +00:00
Maya
099d7a844b Add setup method to extensions 2023-03-19 13:22:24 +00:00
oobabooga
c753261338 Disable stop_at_newline by default 2023-03-18 10:55:57 -03:00
oobabooga
7c945cfe8e Don't include PeftModel every time 2023-03-18 10:55:24 -03:00
oobabooga
e26763a510 Minor changes 2023-03-17 22:56:46 -03:00
Wojtek Kowaluk
7994b580d5 clean up duplicated code 2023-03-18 02:27:26 +01:00
Wojtek Kowaluk
30939e2aee add mps support on apple silicon 2023-03-18 00:56:23 +01:00
oobabooga
9256e937d6 Add some LoRA params 2023-03-17 17:45:28 -03:00
oobabooga
9ed2c4501c Use markdown in the "HTML" tab 2023-03-17 16:06:11 -03:00
oobabooga
f0b26451b4 Add a comment 2023-03-17 13:07:17 -03:00
oobabooga
3bda907727
Merge pull request #366 from oobabooga/lora 
Add LoRA support
 2023-03-17 11:48:48 -03:00
oobabooga
614dad0075 Remove unused import 2023-03-17 11:43:11 -03:00
oobabooga
a717fd709d Sort the imports 2023-03-17 11:42:25 -03:00
oobabooga
29fe7b1c74 Remove LoRA tab, move it into the Parameters menu 2023-03-17 11:39:48 -03:00
oobabooga
214dc6868e Several QoL changes related to LoRA 2023-03-17 11:24:52 -03:00
askmyteapot
53b6a66beb
Update GPTQ_Loader.py 
Correcting decoder layer for renamed class.
 2023-03-17 18:34:13 +10:00
oobabooga
0cecfc684c Add files 2023-03-16 21:35:53 -03:00
oobabooga
104293f411 Add LoRA support 2023-03-16 21:31:39 -03:00
oobabooga
ee164d1821 Don't split the layers in 8-bit mode by default 2023-03-16 18:22:16 -03:00
oobabooga
e085cb4333 Small changes 2023-03-16 13:34:23 -03:00
awoo
83cb20aad8 Add support for --gpu-memory witn --load-in-8bit 2023-03-16 18:42:53 +03:00
oobabooga
1c378965e1 Remove unused imports 2023-03-16 10:18:34 -03:00
oobabooga
a577fb1077 Keep GALACTICA special tokens (#300) 2023-03-16 00:46:59 -03:00
oobabooga
4d64a57092 Add Interface mode tab 2023-03-15 23:29:56 -03:00
oobabooga
66256ac1dd Make the "no GPU has been detected" message more descriptive 2023-03-15 19:31:27 -03:00
oobabooga
c1959c26ee Show/hide the extensions block using javascript 2023-03-15 16:35:28 -03:00
oobabooga
348596f634 Fix broken extensions 2023-03-15 15:11:16 -03:00
oobabooga
c5f14fb9b8 Optimize the HTML generation speed 2023-03-15 14:19:28 -03:00
oobabooga
bf812c4893 Minor fix 2023-03-15 14:05:35 -03:00
oobabooga
05ee323ce5 Rename a file 2023-03-15 13:26:32 -03:00
oobabooga
d30a14087f Further reorganize the UI 2023-03-15 13:24:54 -03:00
oobabooga
cf2da86352 Prevent *Is typing* from disappearing instantly while streaming 2023-03-15 12:51:13 -03:00
oobabooga
ec972b85d1 Move all css/js into separate files 2023-03-15 12:35:11 -03:00
oobabooga
693b53d957 Merge branch 'main' into HideLord-main 2023-03-15 12:08:56 -03:00
oobabooga
1413931705 Add a header bar and redesign the interface (#293) 2023-03-15 12:01:32 -03:00
oobabooga
9d6a625bd6 Add 'hallucinations' filter #326 
This breaks the API since a new parameter has been added.
It should be a one-line fix. See api-example.py.
 2023-03-15 11:10:35 -03:00
oobabooga
afc5339510
Remove "eval" statements from text generation functions 2023-03-14 16:04:17 -03:00
oobabooga
265ba384b7 Rename a file, add deprecation warning for --load-in-4bit 2023-03-14 07:56:31 -03:00
oobabooga
3da73e409f Merge branch 'main' into Zerogoki00-opt4-bit 2023-03-14 07:50:36 -03:00
oobabooga
3fb8196e16 Implement "*Is recording a voice message...*" for TTS #303 2023-03-13 22:28:00 -03:00
oobabooga
518e5c4244 Some minor fixes to the GPTQ loader 2023-03-13 16:45:08 -03:00
Ayanami Rei
8778b756e6 use updated load_quantized 2023-03-13 22:11:40 +03:00
Ayanami Rei
a6a6522b6a determine model type from model name 2023-03-13 22:11:32 +03:00
Ayanami Rei
b6c5c57f2e remove default value from argument 2023-03-13 22:11:08 +03:00
Alexander Hristov Hristov
63c5a139a2
Merge branch 'main' into main 2023-03-13 19:50:08 +02:00
Ayanami Rei
e1c952c41c make argument non case-sensitive 2023-03-13 20:22:38 +03:00
Ayanami Rei
3c9afd5ca3 rename method 2023-03-13 20:14:40 +03:00
Ayanami Rei
1b99ed61bc add argument --gptq-model-type and remove duplicate arguments 2023-03-13 20:01:34 +03:00
Ayanami Rei
edbc61139f use new quant loader 2023-03-13 20:00:38 +03:00
Ayanami Rei
345b6dee8c refactor quant models loader and add support of OPT 2023-03-13 19:59:57 +03:00
oobabooga
66b6971b61 Update README 2023-03-13 12:44:18 -03:00
oobabooga
ddea518e0f Document --auto-launch 2023-03-13 12:43:33 -03:00
oobabooga
372363bc3d Fix GPTQ load_quant call on Windows 2023-03-13 12:07:02 -03:00
oobabooga
0c224cf4f4 Fix GALACTICA (#285) 2023-03-13 10:32:28 -03:00
oobabooga
2c4699a7e9 Change a comment 2023-03-13 00:20:02 -03:00
oobabooga
0a7acb3bd9 Remove redundant comments 2023-03-13 00:12:21 -03:00
oobabooga
77294b27dd Use str(Path) instead of os.path.abspath(Path) 2023-03-13 00:08:01 -03:00
oobabooga
b9e0712b92 Fix Open Assistant 2023-03-12 23:58:25 -03:00
oobabooga
1ddcd4d0ba Clean up silero_tts 
This should only be used with --no-stream.

The shared.still_streaming implementation was faulty by design:
output_modifier should never be called when streaming is already over.
 2023-03-12 23:42:49 -03:00
HideLord
683556f411 Adding markdown support and slight refactoring. 2023-03-12 21:34:09 +02:00
oobabooga
cebe8b390d Remove useless "substring_found" variable 2023-03-12 15:50:38 -03:00
oobabooga
4bcd675ccd Add *Is typing...* to regenerate as well 2023-03-12 15:23:33 -03:00
oobabooga
c7aa51faa6 Use a list of eos_tokens instead of just a number 
This might be the cause of LLaMA ramblings that some people have experienced.
 2023-03-12 14:54:58 -03:00
oobabooga
d8bea766d7
Merge pull request #192 from xanthousm/main 
Add text generation stream status to shared module, use for better TTS with auto-play
 2023-03-12 13:40:16 -03:00
oobabooga
fda376d9c3 Use os.path.abspath() instead of str() 2023-03-12 12:41:04 -03:00
HideLord
8403152257 Fixing compatibility with GPTQ repo commit 2f667f7da051967566a5fb0546f8614bcd3a1ccd. Expects string and breaks on 2023-03-12 17:28:15 +02:00
oobabooga
f3b00dd165
Merge pull request #224 from ItsLogic/llama-bits 
Allow users to load 2, 3 and 4 bit llama models
 2023-03-12 11:23:50 -03:00
oobabooga
65dda28c9d Rename --llama-bits to --gptq-bits 2023-03-12 11:19:07 -03:00
oobabooga
fed3617f07 Move LLaMA 4-bit into a separate file 2023-03-12 11:12:34 -03:00
oobabooga
0ac562bdba Add a default prompt for OpenAssistant oasst-sft-1-pythia-12b #253 2023-03-12 10:46:16 -03:00
oobabooga
78901d522b Remove unused imports 2023-03-12 08:59:05 -03:00
Xan
b3e10e47c0 Fix merge conflict in text_generation 
- Need to update `shared.still_streaming = False` before the final `yield formatted_outputs`, shifted the position of some yields.
 2023-03-12 18:56:35 +11:00
oobabooga
ad14f0e499 Fix regenerate (provisory way) 2023-03-12 03:42:29 -03:00
oobabooga
6e12068ba2
Merge pull request #258 from lxe/lxe/utf8 
Load and save character files and chat history in UTF-8
 2023-03-12 03:28:49 -03:00
oobabooga
e2da6b9685 Fix You You You appearing in chat mode 2023-03-12 03:25:56 -03:00
oobabooga
bcf0075278
Merge pull request #235 from xanthousm/Quality_of_life-main 
--auto-launch and "Is typing..."
 2023-03-12 03:12:56 -03:00
Aleksey Smolenchuk
3f7c3d6559
No need to set encoding on binary read 2023-03-11 22:10:57 -08:00
oobabooga
341e135036 Various fixes in chat mode 2023-03-12 02:53:08 -03:00
Aleksey Smolenchuk
3baf5fc700
Load and save chat history in utf-8 2023-03-11 21:40:01 -08:00
oobabooga
b0e8cb8c88 Various fixes in chat mode 2023-03-12 02:31:45 -03:00
unknown
433f6350bc Load and save character files in UTF-8 2023-03-11 21:23:05 -08:00
oobabooga
0bd5430988 Use 'with' statement to better handle streaming memory 2023-03-12 02:04:28 -03:00
oobabooga
37f0166b2d Fix memory leak in new streaming (second attempt) 2023-03-11 23:14:49 -03:00
oobabooga
92fe947721 Merge branch 'main' into new-streaming 2023-03-11 19:59:45 -03:00