Commit Graph

1826 Commits

Author SHA1 Message Date
Luis Lopez
0dbc3d9b2c
Fix get_documents_ids_distances return error when n_results = 0 (#2347) 2023-05-25 23:25:36 -03:00
jllllll
07a4f0569f
Update README.md to account for BnB Windows wheel (#2341) 2023-05-25 18:44:26 -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
fc33216477 Small fix for n_ctx in llama.cpp 2023-05-25 13:55:51 -03:00
oobabooga
35009c32f0 Beautify all CSS 2023-05-25 13:12:34 -03:00
oobabooga
231305d0f5
Update README.md 2023-05-25 12:05:08 -03:00
oobabooga
37d4ad012b Add a button for rendering markdown for any model 2023-05-25 11:59:27 -03:00
oobabooga
9a43656a50
Add bitsandbytes note 2023-05-25 11:21:52 -03:00
oobabooga
548f05e106 Add windows bitsandbytes wheel by jllllll 2023-05-25 10:48:22 -03:00
DGdev91
cf088566f8
Make llama.cpp read prompt size and seed from settings (#2299) 2023-05-25 10:29:31 -03:00
Luis Lopez
ee674afa50
Add superbooga time weighted history retrieval (#2080) 2023-05-25 10:22:45 -03:00
oobabooga
a04266161d
Update README.md 2023-05-25 01:23:46 -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
eiery
9967e08b1f
update llama-cpp-python to v0.1.53 for ggml v3, fixes #2245 (#2264) 2023-05-24 10:25:28 -03:00
Gabriel Terrien
e50ade438a
FIX silero_tts/elevenlabs_tts activation/deactivation (#2313) 2023-05-24 10:06:38 -03:00
Gabriel Terrien
fc116711b0
FIX save_model_settings function to also update shared.model_config (#2282) 2023-05-24 10:01:07 -03:00
flurb18
d37a28730d
Beginning of multi-user support (#2262)
Adds a lock to generate_reply
2023-05-24 09:38:20 -03:00
Anthony K
7dc87984a2
Fix spelling mistake in new name var of chat api (#2309) 2023-05-23 23:03:03 -03:00
oobabooga
1490c0af68 Remove RWKV from requirements.txt 2023-05-23 20:49:20 -03:00
Gabriel Terrien
7aed53559a
Support of the --gradio-auth flag (#2283) 2023-05-23 20:39:26 -03:00
Atinoda
4155aaa96a
Add mention to alternative docker repository (#2145) 2023-05-23 20:35:53 -03:00
matatonic
9714072692
[extensions/openai] use instruction templates with chat_completions (#2291) 2023-05-23 19:58:41 -03:00
oobabooga
74aae34beb Allow passing your name to the chat API 2023-05-23 19:39:18 -03:00
oobabooga
fb6a00f4e5 Small AutoGPTQ fix 2023-05-23 15:20:01 -03:00
oobabooga
c2d2ef7c13
Update Generation-parameters.md 2023-05-23 02:11:28 -03:00
oobabooga
b0845ae4e8
Update RWKV-model.md 2023-05-23 02:10:08 -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
oobabooga
8b9ba3d7b4 Fix a typo 2023-05-22 20:13:03 -03:00
Gabriel Terrien
0f51b64bb3
Add a "dark_theme" option to settings.json (#2288) 2023-05-22 19:45:11 -03:00
oobabooga
c5446ae0e2 Fix a link 2023-05-22 19:38:34 -03:00
oobabooga
c0fd7f3257
Add mirostat parameters for llama.cpp (#2287) 2023-05-22 19:37:24 -03:00
oobabooga
ec7437f00a
Better way to toggle light/dark mode 2023-05-22 03:19:01 -03:00
oobabooga
d46f5a58a3 Add a button for toggling dark/light mode 2023-05-22 03:11:44 -03:00
dependabot[bot]
baf75356d4
Bump transformers from 4.29.1 to 4.29.2 (#2268) 2023-05-22 02:50:18 -03:00
oobabooga
4372eb228c Increase the interface area by 10px 2023-05-22 00:55:33 -03:00
oobabooga
753f6c5250 Attempt at making interface restart more robust 2023-05-22 00:26:07 -03:00
oobabooga
30225b9dd0 Fix --no-stream queue bug 2023-05-22 00:02:59 -03:00
oobabooga
288912baf1 Add a description for the extensions checkbox group 2023-05-21 23:33:37 -03:00
oobabooga
6e77844733 Add a description for penalty_alpha 2023-05-21 23:09:30 -03:00
oobabooga
d63ef59a0f Apply LLaMA-Precise preset to Vicuna by default 2023-05-21 23:00:42 -03:00
oobabooga
e3d578502a Improve "Chat settings" tab appearance a bit 2023-05-21 22:58:14 -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