dnrops
/
llama.swift
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Commit Graph

  • 25fbc2ea65
         Merge 34e3d06b81 into e2c1db856e #6 Frederik Vogel 2023-05-24 14:57:24 +0900
  • 34e3d06b81 Add missing session parameters #6 Vogel Frederik 2023-05-24 14:04:49 +0900
  • 4fa0531a26 Update llma code to llama.cpp version master-ea60007 Vogel Frederik 2023-05-21 03:19:19 +0900
  • e2c1db856e
         Merge pull request #5 from joshluongo/v2 v2 Alex Rozanski 2023-05-13 15:05:23 +0100
  • 6501877be1
         Updated "Coquille" to use a tagged version instead of a branch. #5 Josh Luongo 2023-05-13 19:59:24 +1000
  • 74eb4678ad fix error handling in LlamaEvent master 1.1.1 Alex Rozanski 2023-05-03 09:01:46 +0100
  • 616a2b9dc9
         add note about CameLLM to README Alex Rozanski 2023-04-26 13:43:13 +0100
  • 67bb47170f fix file type enum conversion in quantization Alex Rozanski 2023-04-21 10:48:49 +0100
  • d1bbd85ccd support running conversion scripts with dependent scripts Alex Rozanski 2023-04-21 10:33:55 +0100
  • b2ba02e0e9 update conversion scripts Alex Rozanski 2023-04-21 10:07:10 +0100
  • b2d1236c0f add keepModelInMemory parameter to config for use_mlock Alex Rozanski 2023-04-21 02:34:14 +0100
  • 1c7b167a63 add missing withSeed() config builder function Alex Rozanski 2023-04-20 20:24:37 +0100
  • 0d37feee62 improve config API Alex Rozanski 2023-04-20 01:47:46 +0100
  • dc935dad14 merge all SessionConfig params with defaults Alex Rozanski 2023-04-20 01:03:55 +0100
  • 0707766c6e make SessionConfig parameters mutable Alex Rozanski 2023-04-19 14:47:19 +0100
  • 7dae88f2b1 make SessionConfig.init() public; add LlamaSessionConfig.default Alex Rozanski 2023-04-19 14:36:53 +0100
  • 37043c80f6 support configuration of hyperparams in session Alex Rozanski 2023-04-19 10:11:37 +0100
  • a233b9fcec
         update intro section in README Alex Rozanski 2023-04-18 13:15:00 +0100
  • b72e4b337f remove more unused files Alex Rozanski 2023-04-18 13:09:22 +0100
  • ec90d7b85e Merge remote-tracking branch 'llama.cpp/master' into v2 Alex Rozanski 2023-04-18 09:34:22 +0100
  • a27a4559b4 generalise conversion implementation Alex Rozanski 2023-04-18 08:32:03 +0100
  • 42747220b4
         Do not close file after mmap (Windows version) (#1034) Ivan Komarov 2023-04-18 03:15:50 +0200
  • e9298af389
         readme : add Ruby bindings (#1029) Atsushi Tatsuma 2023-04-18 04:34:35 +0900
  • 4ad73137a1
         add 4_0 to default outfile namestr dict (#1031) Cameron 2023-04-17 11:26:23 -0700
  • 315a95a4d3
         Add LoRA support (#820) slaren 2023-04-17 17:28:55 +0200
  • efd05648c8
         llama : well-defined static initialization of complex objects (#927) Arik Poznanski 2023-04-17 17:41:53 +0300
  • eb17a026fd
         quantize-stats : fix bug in --type argument Georgi Gerganov 2023-04-17 17:31:06 +0300
  • 69b740289f
         ggml : avoid using ggml_fp16_to_fp32() and ggml_fp32_to_fp16() in ggml.c Georgi Gerganov 2023-04-17 16:16:23 +0300
  • f266259ad9
         Speedup the AVX-512 implementation of ggml_vec_dot_q4_0() (#933) Ivan Komarov 2023-04-17 15:10:57 +0200
  • 47f61aaa5f
         Fix: do not close file on mmap (#1017) slaren 2023-04-16 21:27:38 +0200
  • 3173a62eb9
         stdout : vertical align outputs for better readibility Georgi Gerganov 2023-04-16 13:58:48 +0300
  • 489537e6cf
         examples: add missing <ctime> include for time() (#1011) Pavol Rusnak 2023-04-16 12:13:00 +0200
  • 2d3481c721
         Fix msys2 build error and warnings (#1009) nanahi 2023-04-16 17:13:42 +0800
  • 74f5899df4
         convert.py: Fix loading safetensors and ggml format on Windows (#991) comex 2023-04-15 14:53:21 -0700
  • 2f7c8e014e
         Fix potential int8 overflow in non-SIMD vec_dot (#986) Stephan Walter 2023-04-15 18:28:56 +0000
  • 0ad964631f
         Refactor ggml.c for future tensor types (#1001) Stephan Walter 2023-04-15 16:25:38 +0000
  • e95b6554b4
         ggml : add Q8_0 quantization for intermediate results (#951) Georgi Gerganov 2023-04-15 17:53:22 +0300
  • aa485cee33
         ggml : use posix_memalign on non-Windows env Georgi Gerganov 2023-04-15 14:25:45 +0300
  • c12b14b77f
         benchmark : fix result validation in benchmark-q4_0-matmult (#987) Ivan Komarov 2023-04-15 07:51:54 +0200
  • 106faaf297
         cmake : add finding the OpenBLAS header file (#992) katsu560 2023-04-15 14:51:11 +0900
  • c85e03d12e
         Revert "main : alternative instruct mode (Vicuna support, etc.) (#863)" (#982) Pavol Rusnak 2023-04-14 21:58:43 +0200
  • 489093548c
         py : bump sentencepiece to 0.1.98 to support Python 3.11 (#976) Pavol Rusnak 2023-04-14 21:46:49 +0200
  • 93265e988a
         make : fix dependencies, use auto variables (#983) Stephan Walter 2023-04-14 19:39:48 +0000
  • c56b715269
         Expose type name from ggml (#970) Pavol Rusnak 2023-04-14 20:05:37 +0200
  • f4d277ae17
         main : alternative instruct mode (Vicuna support, etc.) (#863) Tomáš Pazdiora 2023-04-14 17:19:17 +0200
  • c9a59b70a5
         ggml : add unary and binary map operations (#874) Kerfuffle 2023-04-14 08:43:55 -0600
  • a32f7acc9f
         py : cleanup dependencies (#962) Pavol Rusnak 2023-04-14 15:37:11 +0200
  • 43ffdefb74
         py : fix flake8 and isort nitpicks (#960) Pavol Rusnak 2023-04-14 14:23:21 +0200
  • ed25d79c76
         fix build.yml Alex Rozanski 2023-04-14 12:03:44 +0100
  • 604a1a9ec4
         add notes about v2 to the README Alex Rozanski 2023-04-14 12:01:08 +0100
  • 1623a6e9b4
         ggml : minor Georgi Gerganov 2023-04-14 13:31:29 +0300
  • c14e0d2f23
         ggml : always allocate buffers with size multiple of GGML_MEM_ALIGN Georgi Gerganov 2023-04-14 13:31:15 +0300
  • 723dac55fa
         py : new conversion script (#545) comex 2023-04-14 00:03:03 -0700
  • 0f07cacb05
         ggml : fix q4_1 dot product types Georgi Gerganov 2023-04-14 09:45:42 +0300
  • c5d70f5c9e
         ggml : optimize rope function to avoid call powf in the tight loop (#807) Howard Su 2023-04-14 14:24:52 +0800
  • be87b6ed20
         perplexity : add support for batch size to `--perplexity` (#407) Gary Linscott 2023-04-13 14:50:42 -0700
  • 0e07e6a839
         common : remove unnecessary includes (#947) CRD716 2023-04-13 10:39:25 -0500
  • a3a2a0eda8
         ggml : add GGML_DEFAULT_N_THREADS Georgi Gerganov 2023-04-13 18:36:40 +0300
  • d990e3fffc
         ggml : speed-up ggml_vec_dot_q4_1() ARM_NEON + 32-bit ARM support (#900) Georgi Gerganov 2023-04-13 18:32:36 +0300
  • 9190e8eac8
         llama : merge llama_internal.h into llama.h Georgi Gerganov 2023-04-13 18:04:45 +0300
  • c85980acd0
         gitignore : benchmark Georgi Gerganov 2023-04-13 18:01:22 +0300
  • 6232f2d7fd
         ggml : optimize non-SIMD Q4_0 vector dot product (#703) Stephan Walter 2023-04-13 14:59:50 +0000
  • 6c248707f5
         ggml : introduce GGML_ALIGNED_MALLOC/GGML_ALIGNED_FREE macros (#884) Pavol Rusnak 2023-04-13 16:08:32 +0200
  • 8cda5c981d
         fix whitespace (#944) CRD716 2023-04-13 09:03:57 -0500
  • ec29272175
         readme : remove python 3.10 warning (#929) CRD716 2023-04-13 08:59:53 -0500
  • 7e941b95eb
         readme : llama node binding (#911) Genkagaku.GPT 2023-04-13 21:54:27 +0800
  • c729ff730a
         flake.nix: add all binaries from bin (#848) Pavol Rusnak 2023-04-13 15:49:05 +0200
  • 4579af95e8
         zig : update build.zig (#872) Judd 2023-04-13 21:43:22 +0800
  • 8c3ffc2f04
         ggml : update cblas_sgemm columns var to be more reasonable (#838) Vladimir 2023-04-13 15:24:30 +0200
  • 107980d970
         examples : add -n to alpaca and gpt4all scripts (#706) niansa/tuxifan 2023-04-13 15:03:39 +0200
  • 585d91a156
         cmake : add explicit F16C option (x86) (#576) anzz1 2023-04-13 15:48:21 +0300
  • 95ea26f6e9
         benchmark : add tool for timing q4_0 matrix multiplication (#653) SebastianApel 2023-04-13 14:46:23 +0200
  • 82d146df9b
         do not force the prompt file to end with a new line (#908) Pavol Rusnak 2023-04-13 11:33:16 +0200
  • e7f6997f89
         Don't crash on ftype (formerly f16) == 4 (#917) Stephan Walter 2023-04-12 15:06:16 +0000
  • f76cb3a34d
         readme : change "GPU support" link to discussion Georgi Gerganov 2023-04-12 14:48:57 +0300
  • 782438070f
         readme : update hot topics with link to "GPU support" issue Georgi Gerganov 2023-04-12 14:31:12 +0300
  • 4dbbd40750
         readme: link to sha256sums file (#902) Nicolai Weitkemper 2023-04-12 08:46:20 +0200
  • 8b679987cd
         Fix whitespace, add .editorconfig, add GitHub workflow (#883) Pavol Rusnak 2023-04-11 21:45:44 +0200
  • 3e6e70d8e8
         Add enum llama_ftype, sync ggml_type to model files (#709) Stephan Walter 2023-04-11 15:03:51 +0000
  • 2663d2c678
         Windows fixes (#890) comex 2023-04-11 06:19:54 -0700
  • 140fc89987
         Create CODE_OF_CONDUCT.md Alex Rozanski 2023-04-11 13:56:19 +0100
  • a0caa34b16
         Add BAIR's Koala to supported models (#877) qouoq 2023-04-11 04:41:53 +0800
  • 461ba9e66e
         ggml : fix WASM build Georgi Gerganov 2023-04-10 23:20:01 +0300
  • c3ac702e5e
         ggml : add ggml_cont() + optimize ggml_cpy() for contiguous dst Georgi Gerganov 2023-04-10 22:40:28 +0300
  • 9d634ef452
         ggml : remove trailing whitespaces Georgi Gerganov 2023-04-10 19:32:45 +0300
  • d9a239c410
         Simplify to include lower-case windows.h always, fix compile on mingw32 (#747) Marco Matthies 2023-04-10 19:57:59 +0200
  • 684da25926
         ggml : fix quantize_row_q4_1() ARM_NEON (close #876) Georgi Gerganov 2023-04-10 19:29:48 +0300
  • 977c0bc7fc put real conversion script back Alex Rozanski 2023-04-10 05:03:01 +0100
  • 52295c2456 add cancellation support Alex Rozanski 2023-04-10 04:29:18 +0100
  • e5c9314bc9 fix `test` part of convert pipeline Alex Rozanski 2023-04-10 04:19:37 +0100
  • 3ac7cecb5f use dummy script again Alex Rozanski 2023-04-10 04:15:56 +0100
  • 57da9af638 use v0.3 of Coquille Alex Rozanski 2023-04-10 04:14:44 +0100
  • 4ef35a22d5 fix quantize continuation and add debug message Alex Rozanski 2023-04-10 03:39:32 +0100
  • 9ac69d3a5d remove escaping (already done by Process) Alex Rozanski 2023-04-10 03:35:19 +0100
  • 694a73e740 put tokenizer.model and other model files in correct location Alex Rozanski 2023-04-10 03:19:58 +0100
  • a2fe5ab70d look for tokenizer in parent directory Alex Rozanski 2023-04-10 03:05:56 +0100
  • c461f1a72e escape quotes in arguments Alex Rozanski 2023-04-10 02:52:39 +0100
  • 59389209f5 implement skipping in ConnectedConversionStep Alex Rozanski 2023-04-10 02:39:23 +0100
  • d33fc27065 fix state forwarding in AnyConversionStep Alex Rozanski 2023-04-10 02:37:33 +0100
  • ab10e841bf replace dummy scripts with real convert/quantize Alex Rozanski 2023-04-10 02:03:17 +0100