cturan/llama.cpp @ 95bd60a0a69f57e9a2ff1269667ea484a1a9bb40

Georgi Gerganov fcca0a7004 refact : fix convert script + zero out KV cache to avoid nans (#3523)		2 жил өмнө
..
baby-llama	bc39553c90 build : enable more non-default compiler warnings (#3200)	2 жил өмнө
batched	16bc66d947 llama.cpp : split llama_context_params into model and context params (#3301)	2 жил өмнө
beam-search	16bc66d947 llama.cpp : split llama_context_params into model and context params (#3301)	2 жил өмнө
benchmark	65c2c1c5ab benchmark-matmult : do not use integer abs() on a float (#3277)	2 жил өмнө
convert-llama2c-to-ggml	3aefaab9e5 check C++ code with -Wmissing-declarations (#3184)	2 жил өмнө
embd-input	16bc66d947 llama.cpp : split llama_context_params into model and context params (#3301)	2 жил өмнө
embedding	16bc66d947 llama.cpp : split llama_context_params into model and context params (#3301)	2 жил өмнө
export-lora	0e76a8992c train : finetune LORA (#2632)	2 жил өмнө
finetune	f72f8f22c9 finetune : readme fix typo (#3465)	2 жил өмнө
gguf	3aefaab9e5 check C++ code with -Wmissing-declarations (#3184)	2 жил өмнө
gptneox-wip	20c7e1e804 gguf : fix a few general keys (#3341)	2 жил өмнө
infill	c97f01c362 infill : add new example + extend server API (#3296)	2 жил өмнө
jeopardy	a8777ad84e parallel : add option to load external prompt file (#3416)	2 жил өмнө
llama-bench	bc39553c90 build : enable more non-default compiler warnings (#3200)	2 жил өмнө
main	8186242b6d main : consistent prefix/suffix coloring (#3425)	2 жил өмнө
main-cmake-pkg	095231dfd3 cmake : fix transient definitions in find pkg (#3411)	2 жил өмнө
metal	6381d4e110 gguf : new file format with flexible meta data (beta) (#2398)	2 жил өмнө
parallel	fcca0a7004 refact : fix convert script + zero out KV cache to avoid nans (#3523)	2 жил өмнө
perplexity	16bc66d947 llama.cpp : split llama_context_params into model and context params (#3301)	2 жил өмнө
quantize	bc39553c90 build : enable more non-default compiler warnings (#3200)	2 жил өмнө
quantize-stats	16bc66d947 llama.cpp : split llama_context_params into model and context params (#3301)	2 жил өмнө
save-load-state	16bc66d947 llama.cpp : split llama_context_params into model and context params (#3301)	2 жил өмнө
server	8e6716a102 api_like_OAI.py : compat with Microsoft Guidance (#2746)	2 жил өмнө
simple	16bc66d947 llama.cpp : split llama_context_params into model and context params (#3301)	2 жил өмнө
speculative	ac2219fef3 llama : fix session saving/loading (#3400)	2 жил өмнө
train-text-from-scratch	0fe321031a gguf : general usability improvements (#3409)	2 жил өмнө
CMakeLists.txt	0e76a8992c train : finetune LORA (#2632)	2 жил өмнө
Miku.sh	019fe257bb MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)	2 жил өмнө
alpaca.sh	a17a2683d8 alpaca.sh : update model file name (#2074)	2 жил өмнө
chat-13B.bat	d9ad104440 Create chat-13B.bat (#592)	2 жил өмнө
chat-13B.sh	6daa09d879 examples : read chat prompts from a template file (#1196)	2 жил өмнө
chat-persistent.sh	ac2219fef3 llama : fix session saving/loading (#3400)	2 жил өмнө
chat-vicuna.sh	c36e81da62 examples : add chat-vicuna.sh (#1854)	2 жил өмнө
chat.sh	8341a25957 main : log file (#2748)	2 жил өмнө
gpt4all.sh	107980d970 examples : add -n to alpaca and gpt4all scripts (#706)	2 жил өмнө
json-schema-to-grammar.py	7c2227a197 chmod : make scripts executable (#2675)	2 жил өмнө
llama.vim	2d7baaf50f vim : streaming and more (#2495)	2 жил өмнө
llama2-13b.sh	73643f5fb1 gitignore : changes for Poetry users + chat examples (#2284)	2 жил өмнө
llama2.sh	73643f5fb1 gitignore : changes for Poetry users + chat examples (#2284)	2 жил өмнө
llm.vim	ad9ddcff6e llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)	2 жил өмнө
make-ggml.py	ac43576124 make-ggml.py : compatibility with more models and GGUF (#3290)	2 жил өмнө
reason-act.sh	7c2227a197 chmod : make scripts executable (#2675)	2 жил өмнө
server-llama2-13B.sh	7c2227a197 chmod : make scripts executable (#2675)	2 жил өмнө