ik_llama.cpp.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Expand)	Author
2024-05-08	ggml : introduce bfloat16 support (#6412)	Justine Tunney
2024-02-25	code : normalize enum names (#5697)	Georgi Gerganov
2024-02-13	finetune : rename feed-forward tensors (w1/w2/w3) (#4839)	Daniel Bevenius
2024-02-12	sync : ggml (#5452)	Georgi Gerganov
2024-01-22	finetune : print sample-start/include-sample-start (#5072)	Daniel Bevenius
2024-01-16	finetune : add training data file to log message (#4979)	Daniel Bevenius
2024-01-16	finetune : use LLAMA_FILE_MAGIC_GGLA (#4961)	Daniel Bevenius
2024-01-04	finetune : remove unused includes (#4756)	Daniel Bevenius
2023-12-27	finetune : fix output formatting in print_params (#4653)	Daniel Bevenius
2023-12-21	ggml : change ggml_scale to take a float instead of tensor (#4573)	Georgi Gerganov
2023-12-17	finetune : keep allocs alive until all allocations are done (#4486)	slaren
2023-12-14	ggml : remove n_dims from ggml_tensor (#4469)	slaren
2023-11-19	Revert "finetune : add --n-gpu-layers flag info to --help (#4128)"	Georgi Gerganov
2023-11-19	finetune : add --n-gpu-layers flag info to --help (#4128)	Clark Saben
2023-11-17	train : move number of gpu layers argument parsing to common/train.cpp (#4074)	Jiří Podivín
2023-11-17	finetune : zero the loraB initial vectors (#4082)	Andrew Godfrey
2023-11-13	sync : ggml (backend v2) (#3912)	Georgi Gerganov
2023-11-07	ggml : fix backward rope after YaRN (#3974)	xaedes
2023-11-01	llama : implement YaRN RoPE scaling (#2268)	cebtenzzre
2023-11-01	finetune : add -ngl parameter (#3762)	Andrew Godfrey
2023-10-13	ggml : add context enumeration functions (#3605)	slaren
2023-10-02	finetune : fix #3404 (#3437)	xaedes
2023-09-29	train : fix KQ_pos allocation (#3392)	Georgi Gerganov
2023-09-28	llama.cpp : split llama_context_params into model and context params (#3301)	slaren
2023-09-28	train : finetune LORA (#2632)	xaedes