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
..
callbacks.py	optimize stopping strings processing (#1625)	2023-05-02 01:21:54 -03:00
chat.py	Move the rstrips	2023-04-26 17:17:22 -03:00
deepspeed_parameters.py	Fix deepspeed (oops)	2023-02-02 10:39:37 -03:00
evaluate.py	Fix evaluate comment saving	2023-04-21 12:34:08 -03:00
extensions.py	Only show extension in UI if it has an ui() function	2023-05-02 19:20:02 -03:00
GPTQ_loader.py	LLaVA support (#1487)	2023-04-23 20:32:22 -03:00
html_generator.py	Readability	2023-04-16 21:26:19 -03:00
llama_attn_hijack.py	Added xformers support to Llama (#950)	2023-04-09 23:08:40 -03:00
llamacpp_model.py	added no_mmap & mlock parameters to llama.cpp and removed llamacpp_model_alternative (#1649)	2023-05-02 18:25:28 -03:00
LoRA.py	Load more than one LoRA with --lora, fix a bug	2023-04-25 22:58:48 -03:00
models.py	added no_mmap & mlock parameters to llama.cpp and removed llamacpp_model_alternative (#1649)	2023-05-02 18:25:28 -03:00
monkey_patch_gptq_lora.py	Make universal tokenizer, xformers, sdp-attention apply to monkey patch	2023-04-25 23:18:11 -03:00
RWKV.py	Make the code more like PEP8 for readability (#862)	2023-04-07 00:15:45 -03:00
shared.py	added no_mmap & mlock parameters to llama.cpp and removed llamacpp_model_alternative (#1649)	2023-05-02 18:25:28 -03:00
text_generation.py	LLaVA: small fixes (#1664)	2023-05-02 23:12:22 -03:00
training.py	LoRA trainer improvements part 5 (#1546)	2023-04-25 21:27:30 -03:00
ui.py	Precise prompts for instruct mode	2023-04-26 03:21:53 -03:00