oobabooga
cec5fb0ef6
Failed attempt at evaluating exllama_hf perplexity
2023-06-24 12:02:25 -03:00
快乐的我531
e356f69b36
Make stop_everything work with non-streamed generation ( #2848 )
2023-06-24 11:19:16 -03:00
oobabooga
ec482f3dae
Apply input extensions after yielding *Is typing...*
2023-06-24 11:07:11 -03:00
oobabooga
3e80f2aceb
Apply the output extensions only once
...
Relevant for google translate, silero
2023-06-24 10:59:07 -03:00
missionfloyd
51a388fa34
Organize chat history/character import menu ( #2845 )
...
* Organize character import menu
* Move Chat history upload/download labels
2023-06-24 09:55:02 -03:00
oobabooga
8bb3bb39b3
Implement stopping string search in string space ( #2847 )
2023-06-24 09:43:00 -03:00
oobabooga
3ae9af01aa
Add --no_use_cuda_fp16 param for AutoGPTQ
2023-06-23 12:22:56 -03:00
Panchovix
5646690769
Fix some models not loading on exllama_hf ( #2835 )
2023-06-23 11:31:02 -03:00
oobabooga
383c50f05b
Replace old presets with the results of Preset Arena ( #2830 )
2023-06-23 01:48:29 -03:00
Panchovix
b4a38c24b7
Fix Multi-GPU not working on exllama_hf ( #2803 )
2023-06-22 16:05:25 -03:00
LarryVRH
580c1ee748
Implement a demo HF wrapper for exllama to utilize existing HF transformers decoding. ( #2777 )
2023-06-21 15:31:42 -03:00
EugeoSynthesisThirtyTwo
7625c6de89
fix usage of self in classmethod ( #2781 )
2023-06-20 16:18:42 -03:00
MikoAL
c40932eb39
Added Falcon LoRA training support ( #2684 )
...
I am 50% sure this will work
2023-06-20 01:03:44 -03:00
FartyPants
ce86f726e9
Added saving of training logs to training_log.json ( #2769 )
2023-06-20 00:47:36 -03:00
Cebtenzzre
59e7ecb198
llama.cpp: implement ban_eos_token via logits_processor ( #2765 )
2023-06-19 21:31:19 -03:00
oobabooga
eb30f4441f
Add ExLlama+LoRA support ( #2756 )
2023-06-19 12:31:24 -03:00
oobabooga
5f418f6171
Fix a memory leak (credits for the fix: Ph0rk0z)
2023-06-19 01:19:28 -03:00
ThisIsPIRI
def3b69002
Fix loading condition for universal llama tokenizer ( #2753 )
2023-06-18 18:14:06 -03:00
oobabooga
09c781b16f
Add modules/block_requests.py
...
This has become unnecessary, but it could be useful in the future
for other libraries.
2023-06-18 16:31:14 -03:00
Forkoz
3cae1221d4
Update exllama.py - Respect model dir parameter ( #2744 )
2023-06-18 13:26:30 -03:00
oobabooga
c5641b65d3
Handle leading spaces properly in ExLllama
2023-06-17 19:35:12 -03:00
oobabooga
05a743d6ad
Make llama.cpp use tfs parameter
2023-06-17 19:08:25 -03:00
oobabooga
e19cbea719
Add a variable to modules/shared.py
2023-06-17 19:02:29 -03:00
oobabooga
cbd63eeeff
Fix repeated tokens with exllama
2023-06-17 19:02:08 -03:00
oobabooga
766c760cd7
Use gen_begin_reuse in exllama
2023-06-17 18:00:10 -03:00
oobabooga
b27f83c0e9
Make exllama stoppable
2023-06-16 22:03:23 -03:00
oobabooga
7f06d551a3
Fix streaming callback
2023-06-16 21:44:56 -03:00
oobabooga
5f392122fd
Add gpu_split param to ExLlama
...
Adapted from code created by Ph0rk0z. Thank you Ph0rk0z.
2023-06-16 20:49:36 -03:00
oobabooga
9f40032d32
Add ExLlama support ( #2444 )
2023-06-16 20:35:38 -03:00
oobabooga
dea43685b0
Add some clarifications
2023-06-16 19:10:53 -03:00
oobabooga
7ef6a50e84
Reorganize model loading UI completely ( #2720 )
2023-06-16 19:00:37 -03:00
Tom Jobbins
646b0c889f
AutoGPTQ: Add UI and command line support for disabling fused attention and fused MLP ( #2648 )
2023-06-15 23:59:54 -03:00
oobabooga
2b9a6b9259
Merge remote-tracking branch 'refs/remotes/origin/main'
2023-06-14 18:45:24 -03:00
oobabooga
4d508cbe58
Add some checks to AutoGPTQ loader
2023-06-14 18:44:43 -03:00
FartyPants
56c19e623c
Add LORA name instead of "default" in PeftModel ( #2689 )
2023-06-14 18:29:42 -03:00
oobabooga
474dc7355a
Allow API requests to use parameter presets
2023-06-14 11:32:20 -03:00
oobabooga
e471919e6d
Make llava/minigpt-4 work with AutoGPTQ
2023-06-11 17:56:01 -03:00
oobabooga
f4defde752
Add a menu for installing extensions
2023-06-11 17:11:06 -03:00
oobabooga
ac122832f7
Make dropdown menus more similar to automatic1111
2023-06-11 14:20:16 -03:00
oobabooga
6133675e0f
Add menus for saving presets/characters/instruction templates/prompts ( #2621 )
2023-06-11 12:19:18 -03:00
brandonj60
b04e18d10c
Add Mirostat v2 sampling to transformer models ( #2571 )
2023-06-09 21:26:31 -03:00
oobabooga
6015616338
Style changes
2023-06-06 13:06:05 -03:00
oobabooga
f040073ef1
Handle the case of older autogptq install
2023-06-06 13:05:05 -03:00
oobabooga
bc58dc40bd
Fix a minor bug
2023-06-06 12:57:13 -03:00
oobabooga
00b94847da
Remove softprompt support
2023-06-06 07:42:23 -03:00
oobabooga
0aebc838a0
Don't save the history for 'None' character
2023-06-06 07:21:07 -03:00
oobabooga
9f215523e2
Remove some unused imports
2023-06-06 07:05:46 -03:00
oobabooga
0f0108ce34
Never load the history for default character
2023-06-06 07:00:11 -03:00
oobabooga
11f38b5c2b
Add AutoGPTQ LoRA support
2023-06-05 23:32:57 -03:00
oobabooga
3a5cfe96f0
Increase chat_prompt_size_max
2023-06-05 17:37:37 -03:00
oobabooga
f276d88546
Use AutoGPTQ by default for GPTQ models
2023-06-05 15:41:48 -03:00
oobabooga
9b0e95abeb
Fix "regenerate" when "Start reply with" is set
2023-06-05 11:56:03 -03:00
oobabooga
19f78684e6
Add "Start reply with" feature to chat mode
2023-06-02 13:58:08 -03:00
GralchemOz
f7b07c4705
Fix the missing Chinese character bug ( #2497 )
2023-06-02 13:45:41 -03:00
oobabooga
2f6631195a
Add desc_act checkbox to the UI
2023-06-02 01:45:46 -03:00
LaaZa
9c066601f5
Extend AutoGPTQ support for any GPTQ model ( #1668 )
2023-06-02 01:33:55 -03:00
oobabooga
a83f9aa65b
Update shared.py
2023-06-01 12:08:39 -03:00
oobabooga
b6c407f51d
Don't stream at more than 24 fps
...
This is a performance optimization
2023-05-31 23:41:42 -03:00
Forkoz
9ab90d8b60
Fix warning for qlora ( #2438 )
2023-05-30 11:09:18 -03:00
oobabooga
3578dd3611
Change a warning message
2023-05-29 22:40:54 -03:00
oobabooga
3a6e194bc7
Change a warning message
2023-05-29 22:39:23 -03:00
Luis Lopez
9e7204bef4
Add tail-free and top-a sampling ( #2357 )
2023-05-29 21:40:01 -03:00
oobabooga
1394f44e14
Add triton checkbox for AutoGPTQ
2023-05-29 15:32:45 -03:00
oobabooga
f34d20922c
Minor fix
2023-05-29 13:31:17 -03:00
oobabooga
983eef1e29
Attempt at evaluating falcon perplexity (failed)
2023-05-29 13:28:25 -03:00
Honkware
204731952a
Falcon support (trust-remote-code and autogptq checkboxes) ( #2367 )
...
---------
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-05-29 10:20:18 -03:00
Forkoz
60ae80cf28
Fix hang in tokenizer for AutoGPTQ llama models. ( #2399 )
2023-05-28 23:10:10 -03:00
oobabooga
2f811b1bdf
Change a warning message
2023-05-28 22:48:20 -03:00
oobabooga
9ee1e37121
Fix return message when no model is loaded
2023-05-28 22:46:32 -03:00
oobabooga
00ebea0b2a
Use YAML for presets and settings
2023-05-28 22:34:12 -03:00
oobabooga
acfd876f29
Some qol changes to "Perplexity evaluation"
2023-05-25 15:06:22 -03:00
oobabooga
8efdc01ffb
Better default for compute_dtype
2023-05-25 15:05:53 -03:00
oobabooga
37d4ad012b
Add a button for rendering markdown for any model
2023-05-25 11:59:27 -03:00
DGdev91
cf088566f8
Make llama.cpp read prompt size and seed from settings ( #2299 )
2023-05-25 10:29:31 -03:00
oobabooga
361451ba60
Add --load-in-4bit parameter ( #2320 )
2023-05-25 01:14:13 -03:00
oobabooga
63ce5f9c28
Add back a missing bos token
2023-05-24 13:54:36 -03:00
Alex "mcmonkey" Goodwin
3cd7c5bdd0
LoRA Trainer: train_only_after option to control which part of your input to train on ( #2315 )
2023-05-24 12:43:22 -03:00
flurb18
d37a28730d
Beginning of multi-user support ( #2262 )
...
Adds a lock to generate_reply
2023-05-24 09:38:20 -03:00
Gabriel Terrien
7aed53559a
Support of the --gradio-auth flag ( #2283 )
2023-05-23 20:39:26 -03:00
oobabooga
fb6a00f4e5
Small AutoGPTQ fix
2023-05-23 15:20:01 -03:00
oobabooga
cd3618d7fb
Add support for RWKV in Hugging Face format
2023-05-23 02:07:28 -03:00
oobabooga
75adc110d4
Fix "perplexity evaluation" progress messages
2023-05-23 01:54:52 -03:00
oobabooga
4d94a111d4
memoize load_character to speed up the chat API
2023-05-23 00:50:58 -03:00
Gabriel Terrien
0f51b64bb3
Add a "dark_theme" option to settings.json ( #2288 )
2023-05-22 19:45:11 -03:00
oobabooga
c0fd7f3257
Add mirostat parameters for llama.cpp ( #2287 )
2023-05-22 19:37:24 -03:00
oobabooga
d63ef59a0f
Apply LLaMA-Precise preset to Vicuna by default
2023-05-21 23:00:42 -03:00
oobabooga
dcc3e54005
Various "impersonate" fixes
2023-05-21 22:54:28 -03:00
oobabooga
e116d31180
Prevent unwanted log messages from modules
2023-05-21 22:42:34 -03:00
oobabooga
fb91406e93
Fix generation_attempts continuing after an empty reply
2023-05-21 22:14:50 -03:00
oobabooga
e18534fe12
Fix "continue" in chat-instruct mode
2023-05-21 22:05:59 -03:00
oobabooga
8ac3636966
Add epsilon_cutoff/eta_cutoff parameters ( #2258 )
2023-05-21 15:11:57 -03:00
oobabooga
1e5821bd9e
Fix silero tts autoplay (attempt #2 )
2023-05-21 13:25:11 -03:00
oobabooga
a5d5bb9390
Fix silero tts autoplay
2023-05-21 12:11:59 -03:00
oobabooga
05593a7834
Minor bug fix
2023-05-20 23:22:36 -03:00
Matthew McAllister
ab6acddcc5
Add Save/Delete character buttons ( #1870 )
...
---------
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-05-20 21:48:45 -03:00
oobabooga
c5af549d4b
Add chat API ( #2233 )
2023-05-20 18:42:17 -03:00
Konstantin Gukov
1b52bddfcc
Mitigate UnboundLocalError ( #2136 )
2023-05-19 14:46:18 -03:00
Alex "mcmonkey" Goodwin
50c70e28f0
Lora Trainer improvements, part 6 - slightly better raw text inputs ( #2108 )
2023-05-19 12:58:54 -03:00
oobabooga
9d5025f531
Improve error handling while loading GPTQ models
2023-05-19 11:20:08 -03:00
oobabooga
b667ffa51d
Simplify GPTQ_loader.py
2023-05-17 16:22:56 -03:00
oobabooga
ef10ffc6b4
Add various checks to model loading functions
2023-05-17 16:14:54 -03:00
oobabooga
abd361b3a0
Minor change
2023-05-17 11:33:43 -03:00
oobabooga
21ecc3701e
Avoid a name conflict
2023-05-17 11:23:13 -03:00
oobabooga
fb91c07191
Minor bug fix
2023-05-17 11:16:37 -03:00
oobabooga
1a8151a2b6
Add AutoGPTQ support (basic) ( #2132 )
2023-05-17 11:12:12 -03:00
Alex "mcmonkey" Goodwin
1f50dbe352
Experimental jank multiGPU inference that's 2x faster than native somehow ( #2100 )
2023-05-17 10:41:09 -03:00
oobabooga
ce21804ec7
Allow extensions to define a new tab
2023-05-17 01:31:56 -03:00
oobabooga
a84f499718
Allow extensions to define custom CSS and JS
2023-05-17 00:30:54 -03:00
oobabooga
7584d46c29
Refactor models.py ( #2113 )
2023-05-16 19:52:22 -03:00
oobabooga
5cd6dd4287
Fix no-mmap bug
2023-05-16 17:35:49 -03:00
Forkoz
d205ec9706
Fix Training fails when evaluation dataset is selected ( #2099 )
...
Fixes https://github.com/oobabooga/text-generation-webui/issues/2078 from Googulator
2023-05-16 13:40:19 -03:00
atriantafy
26cf8c2545
add api port options ( #1990 )
2023-05-15 20:44:16 -03:00
Andrei
e657dd342d
Add in-memory cache support for llama.cpp ( #1936 )
2023-05-15 20:19:55 -03:00
Jakub Strnad
0227e738ed
Add settings UI for llama.cpp and fixed reloading of llama.cpp models ( #2087 )
2023-05-15 19:51:23 -03:00
oobabooga
c07215cc08
Improve the default Assistant character
2023-05-15 19:39:08 -03:00
oobabooga
4e66f68115
Create get_max_memory_dict() function
2023-05-15 19:38:27 -03:00
AlphaAtlas
071f0776ad
Add llama.cpp GPU offload option ( #2060 )
2023-05-14 22:58:11 -03:00
oobabooga
3b886f9c9f
Add chat-instruct mode ( #2049 )
2023-05-14 10:43:55 -03:00
oobabooga
df37ba5256
Update impersonate_wrapper
2023-05-12 12:59:48 -03:00
oobabooga
e283ddc559
Change how spaces are handled in continue/generation attempts
2023-05-12 12:50:29 -03:00
oobabooga
2eeb27659d
Fix bug in --cpu-memory
2023-05-12 06:17:07 -03:00
oobabooga
5eaa914e1b
Fix settings.json being ignored because of config.yaml
2023-05-12 06:09:45 -03:00
oobabooga
71693161eb
Better handle spaces in LlamaTokenizer
2023-05-11 17:55:50 -03:00
oobabooga
7221d1389a
Fix a bug
2023-05-11 17:11:10 -03:00
oobabooga
0d36c18f5d
Always return only the new tokens in generation functions
2023-05-11 17:07:20 -03:00
oobabooga
394bb253db
Syntax improvement
2023-05-11 16:27:50 -03:00
oobabooga
f7dbddfff5
Add a variable for tts extensions to use
2023-05-11 16:12:46 -03:00
oobabooga
638c6a65a2
Refactor chat functions ( #2003 )
2023-05-11 15:37:04 -03:00
oobabooga
b7a589afc8
Improve the Metharme prompt
2023-05-10 16:09:32 -03:00
oobabooga
b01c4884cb
Better stopping strings for instruct mode
2023-05-10 14:22:38 -03:00
oobabooga
6a4783afc7
Add markdown table rendering
2023-05-10 13:41:23 -03:00
oobabooga
3316e33d14
Remove unused code
2023-05-10 11:59:59 -03:00
Alexander Dibrov
ec14d9b725
Fix custom_generate_chat_prompt ( #1965 )
2023-05-10 11:29:59 -03:00
oobabooga
32481ec4d6
Fix prompt order in the dropdown
2023-05-10 02:24:09 -03:00
oobabooga
dfd9ba3e90
Remove duplicate code
2023-05-10 02:07:22 -03:00
oobabooga
bdf1274b5d
Remove duplicate code
2023-05-10 01:34:04 -03:00
oobabooga
3913155c1f
Style improvements ( #1957 )
2023-05-09 22:49:39 -03:00
minipasila
334486f527
Added instruct-following template for Metharme ( #1679 )
2023-05-09 22:29:22 -03:00
Carl Kenner
814f754451
Support for MPT, INCITE, WizardLM, StableLM, Galactica, Vicuna, Guanaco, and Baize instruction following ( #1596 )
2023-05-09 20:37:31 -03:00
Wojtab
e9e75a9ec7
Generalize multimodality (llava/minigpt4 7b and 13b now supported) ( #1741 )
2023-05-09 20:18:02 -03:00
Wesley Pyburn
a2b25322f0
Fix trust_remote_code in wrong location ( #1953 )
2023-05-09 19:22:10 -03:00
LaaZa
218bd64bd1
Add the option to not automatically load the selected model ( #1762 )
...
---------
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-05-09 15:52:35 -03:00
Maks
cf6caf1830
Make the RWKV model cache the RNN state between messages ( #1354 )
2023-05-09 11:12:53 -03:00
Kamil Szurant
641500dcb9
Use current input for Impersonate (continue impersonate feature) ( #1147 )
2023-05-09 02:37:42 -03:00
IJumpAround
020fe7b50b
Remove mutable defaults from function signature. ( #1663 )
2023-05-08 22:55:41 -03:00
Matthew McAllister
d78b04f0b4
Add error message when GPTQ-for-LLaMa import fails ( #1871 )
...
---------
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-05-08 22:29:09 -03:00
oobabooga
68dcbc7ebd
Fix chat history handling in instruct mode
2023-05-08 16:41:21 -03:00
Clay Shoaf
79ac94cc2f
fixed LoRA loading issue ( #1865 )
2023-05-08 16:21:55 -03:00
oobabooga
b5260b24f1
Add support for custom chat styles ( #1917 )
2023-05-08 12:35:03 -03:00
EgrorBs
d3ea70f453
More trust_remote_code=trust_remote_code ( #1899 )
2023-05-07 23:48:20 -03:00
oobabooga
56a5969658
Improve the separation between instruct/chat modes ( #1896 )
2023-05-07 23:47:02 -03:00
oobabooga
9754d6a811
Fix an error message
2023-05-07 17:44:05 -03:00
camenduru
ba65a48ec8
trust_remote_code=shared.args.trust_remote_code ( #1891 )
2023-05-07 17:42:44 -03:00
oobabooga
6b67cb6611
Generalize superbooga to chat mode
2023-05-07 15:05:26 -03:00
oobabooga
56f6b7052a
Sort dropdowns numerically
2023-05-05 23:14:56 -03:00
oobabooga
8aafb1f796
Refactor text_generation.py, add support for custom generation functions ( #1817 )
2023-05-05 18:53:03 -03:00
oobabooga
c728f2b5f0
Better handle new line characters in code blocks
2023-05-05 11:22:36 -03:00
oobabooga
00e333d790
Add MOSS support
2023-05-04 23:20:34 -03:00
oobabooga
f673f4a4ca
Change --verbose behavior
2023-05-04 15:56:06 -03:00
oobabooga
97a6a50d98
Use oasst tokenizer instead of universal tokenizer
2023-05-04 15:55:39 -03:00
oobabooga
b6ff138084
Add --checkpoint argument for GPTQ
2023-05-04 15:17:20 -03:00
Mylo
bd531c2dc2
Make --trust-remote-code work for all models ( #1772 )
2023-05-04 02:01:28 -03:00
oobabooga
0e6d17304a
Clearer syntax for instruction-following characters
2023-05-03 22:50:39 -03:00
oobabooga
9c77ab4fc2
Improve some warnings
2023-05-03 22:06:46 -03:00
oobabooga
057b1b2978
Add credits
2023-05-03 21:49:55 -03:00
oobabooga
95d04d6a8d
Better warning messages
2023-05-03 21:43:17 -03:00
oobabooga
f54256e348
Rename no_mmap to no-mmap
2023-05-03 09:50:31 -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
4e09df4034
Only show extension in UI if it has an ui() function
2023-05-02 19:20:02 -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
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
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
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
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
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
eiery
78d1977ebf
add n_batch support for llama.cpp ( #1115 )
2023-04-24 03:46:18 -03:00
oobabooga
b1ee674d75
Make interface state (mostly) persistent on page reload
2023-04-24 03:05:47 -03:00
oobabooga
435f8cc0e7
Simplify some chat functions
2023-04-24 00:47:40 -03:00
Wojtab
12212cf6be
LLaVA support ( #1487 )
2023-04-23 20:32:22 -03:00
Andy Salerno
654933c634
New universal API with streaming/blocking endpoints ( #990 )
...
Previous title: Add api_streaming extension and update api-example-stream to use it
* Merge with latest main
* Add parameter capturing encoder_repetition_penalty
* Change some defaults, minor fixes
* Add --api, --public-api flags
* remove unneeded/broken comment from blocking API startup. The comment is already correctly emitted in try_start_cloudflared by calling the lambda we pass in.
* Update on_start message for blocking_api, it should say 'non-streaming' and not 'streaming'
* Update the API examples
* Change a comment
* Update README
* Remove the gradio API
* Remove unused import
* Minor change
* Remove unused import
---------
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-04-23 15:52:43 -03:00
Alex "mcmonkey" Goodwin
459e725af9
Lora trainer docs ( #1493 )
2023-04-23 12:54:41 -03:00
oobabooga
c0b5c09860
Minor change
2023-04-22 15:15:31 -03:00
oobabooga
fcb594b90e
Don't require llama.cpp models to be placed in subfolders
2023-04-22 14:56:48 -03:00
oobabooga
7438f4f6ba
Change GPTQ triton default settings
2023-04-22 12:27:30 -03:00
USBhost
e1aa9d5173
Support upstream GPTQ once again. ( #1451 )
2023-04-21 12:43:56 -03:00
oobabooga
eddd016449
Minor deletion
2023-04-21 12:41:27 -03:00
oobabooga
d46b9b7c50
Fix evaluate comment saving
2023-04-21 12:34:08 -03:00
oobabooga
5e023ae64d
Change dropdown menu highlight color
2023-04-21 02:47:18 -03:00
oobabooga
c4f4f41389
Add an "Evaluate" tab to calculate the perplexities of models ( #1322 )
2023-04-21 00:20:33 -03:00
oobabooga
7bb9036ac9
Add universal LLaMA tokenizer support
2023-04-19 21:23:51 -03:00
Alex "mcmonkey" Goodwin
ee30625cd1
4-Bit LoRA training + several new training options and fixes
2023-04-19 19:39:03 -03:00
oobabooga
702fe92d42
Increase truncation_length_max value
2023-04-19 17:35:38 -03:00
oobabooga
9d9ae62938
Fix stopping strings in the gradio API
2023-04-19 13:52:21 -03:00
oobabooga
649e4017a5
Style improvements
2023-04-19 00:36:28 -03:00
oobabooga
000f65a2ef
Delete unused file
2023-04-18 04:01:14 -03:00
oobabooga
36f7c022f2
Rename a file
2023-04-18 01:38:33 -03:00
oobabooga
b069bb1f2e
Update monkey_patch_gradio.py
2023-04-18 01:32:42 -03:00
oobabooga
00186f76f4
Monkey patch gradio to prevent it from calling home
2023-04-18 01:13:16 -03:00
Tynan Burke
6a810b16b2
typo in training.py ( #1329 )
2023-04-17 21:40:46 -03:00
oobabooga
ac2973ffc6
Add a warning for --share
2023-04-17 19:34:28 -03:00
oobabooga
c544386824
Reset your name when choosing a character
2023-04-17 13:56:40 -03:00
oobabooga
c3dc348d1c
Don't show 'None' in the LoRA list
2023-04-17 13:52:23 -03:00
oobabooga
89bc540557
Update README
2023-04-17 10:55:35 -03:00
catalpaaa
07de7d0426
Load llamacpp before quantized model ( #1307 )
2023-04-17 10:47:26 -03:00
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
