gpt4all

Commit Graph

Author	SHA1	Message	Date
Adam Treat	b36ea3dde5	Fix up for newer models on reset context. This fixes the model from totally failing after a reset context.	1 year ago
AT	b5971b0d41	Backend prompt dedup (#822 ) * Deduplicated prompt() function code	1 year ago
niansa/tuxifan	8203d65445	Fixed tons of warnings and clazy findings (#811 )	1 year ago
Adam Treat	7ee32d605f	Trying to shrink the copy+paste code and do more code sharing between backend model impl.	1 year ago
niansa	b68d359b4f	Dlopen better implementation management (Version 2)	1 year ago
AT	9c6c09cbd2	Dlopen backend 5 (#779 ) Major change to the backend that allows for pluggable versions of llama.cpp/ggml. This was squashed merged from dlopen_backend_5 where the history is preserved.	1 year ago
Adam Treat	4a317eeb33	Revert "New tokenizer implementation for MPT and GPT-J" This reverts commit `ee3469ba6c`.	1 year ago
Aaron Miller	ee3469ba6c	New tokenizer implementation for MPT and GPT-J Improves output quality by making these tokenizers more closely match the behavior of the huggingface `tokenizers` based BPE tokenizers these models were trained with. Featuring: * Fixed unicode handling (via ICU) * Fixed BPE token merge handling * Complete added vocabulary handling	1 year ago
Adam Treat	80024a029c	Add new reverse prompt for new localdocs context feature.	1 year ago
Juuso Alasuutari	f2528e6f62	llmodel: constify LLModel::threadCount()	1 year ago
aaron miller	08f3bd2a82	backend: fix buffer overrun in repeat penalty code Caught with AddressSanitizer running a basic prompt test against llmodel standalone. This fix allows ASan builds to complete a simple prompt without illegal accesses but there are still notably several leaks.	1 year ago
kuvaus	4f021ebcbb	gpt4all-backend: Add MSVC support to backend (#595 ) * Add MSVC compatibility * Add _MSC_VER macro --------- Co-authored-by: kuvaus <kuvaus@users.noreply.github.com>	1 year ago
Aaron Miller	9aaa355d41	backend: dedupe tokenizing code in mpt/gptj	1 year ago
Aaron Miller	fc2869f0b7	backend: dedupe tokenizing code in gptj/mpt	1 year ago
Aaron Miller	16b7bf01a8	backend: make initial buf_size const in model impls more unifying mpt and gptj code - this one's never written so also changing the name to be clearer	1 year ago
Aaron Miller	0c9b7a6ae8	mpt: use buf in model struct (thread safety)	1 year ago
Adam Treat	8e7b96bd92	Move the llmodel C API to new top-level directory and version it.	1 year ago

17 Commits (b36ea3dde56335cbf4489934ab3b961a7265870d)