284 Commits

Author	SHA1	Message	Date
oobabooga	3c25557ef0	Add tqdm to requirements.txt	2023-03-12 08:48:16 -03:00
oobabooga	501afbc234	Add requests to requirements.txt	2023-03-11 14:47:30 -03:00
oobabooga	fd540b8930	Use new LLaMA implementation (this will break stuff. I am sorry) ... https://github.com/oobabooga/text-generation-webui/wiki/LLaMA-model	2023-03-09 17:59:15 -03:00
oobabooga	8660227e1b	Add top_k to RWKV	2023-03-07 17:24:28 -03:00
oobabooga	153dfeb4dd	Add --rwkv-cuda-on parameter, bump rwkv version	2023-03-06 20:12:54 -03:00
oobabooga	145c725c39	Bump RWKV version	2023-03-05 16:28:21 -03:00
oobabooga	5492e2e9f8	Add sentencepiece	2023-03-05 10:02:24 -03:00
oobabooga	c33715ad5b	Move towards HF LLaMA implementation	2023-03-05 01:20:31 -03:00
oobabooga	bcea196c9d	Bump flexgen version	2023-03-02 12:03:57 -03:00
oobabooga	7a9b4407b0	Settle for 0.0.6 for now	2023-03-01 17:37:14 -03:00
oobabooga	f351dce032	Keep rwkv up to date	2023-03-01 17:36:16 -03:00
oobabooga	9c86a1cd4a	Add RWKV pip package	2023-03-01 11:42:49 -03:00
oobabooga	b16f097466	Add FlexGen to requirements.txt	2023-02-27 08:58:07 -03:00
oobabooga	4548227fb5	Downgrade gradio version (file uploads are broken in 3.19.1)	2023-02-25 22:59:02 -03:00
oobabooga	32f40f3b42	Bump gradio version to 3.19.1	2023-02-25 17:20:03 -03:00
oobabooga	fe1771157f	Properly scrape huggingface for download links (for #122)	2023-02-24 14:06:42 -03:00
oobabooga	55bb5e5ef0	Bump accelerate version	2023-02-18 22:15:47 -03:00
oobabooga	a55e8836f6	Bump gradio version ... It looks uglier, but the old one was bugged and unstable.	2023-02-15 20:20:56 -03:00
oobabooga	3277b751f5	Add softprompt support (for real this time) ... Is this too much voodoo for our purposes?	2023-02-13 15:25:16 -03:00
oobabooga	b4fc8dfa8f	Add safetensors version	2023-02-04 18:58:17 -03:00
oobabooga	3dbebe30b1	Remove deepspeed requirement (only works on Linux for now)	2023-02-03 20:07:13 -03:00
oobabooga	03f084f311	Add safetensors support	2023-02-03 18:36:32 -03:00
oobabooga	03ebfba0fb	Bump bitsandbytes version	2023-02-03 09:29:31 -03:00
oobabooga	224be31a74	Use main bs4 package	2023-02-02 12:20:58 -03:00
oobabooga	cecaebc291	Add bs4 requirement (fixes #47)	2023-02-02 12:18:32 -03:00
oobabooga	d6b2d68527	Remove redundant requirements	2023-02-02 10:40:09 -03:00
81300	a97afa6965	Add DeepSpeed ZeRO-3 integration	2023-02-01 18:48:13 +02:00
oobabooga	414fa9d161	Revert transformers version (gpt-j and opt are broken)	2023-01-26 23:01:13 -03:00
Silver267	ad191e295b	bump transformers ... idk but there seems to be a lot of fixes in the new version, and it's working according to my local tests.	2023-01-25 23:22:20 -05:00
oobabooga	fc73188ec7	Allow specifying your own profile picture in chat mode	2023-01-25 19:37:44 -03:00
oobabooga	3fa14befc5	Bump the gradio version, add back the queue	2023-01-25 16:10:35 -03:00
oobabooga	4067cecf67	Bump bitsandbytes version	2023-01-20 12:51:49 -03:00
oobabooga	fed7233ff4	Add script to download models	2023-01-06 19:57:31 -03:00
oobabooga	874cd6ff3f	Add the requirements.txt file (duh)	2023-01-06 00:25:33 -03:00