Commit graph

  • 9f4505a0c6 fixed some bugs FSSRepo 2023-05-03 14:25:14 -06:00
  • 799fdc1b5d
    ggml : vectorize Q8_0 quantization master-799fdc1 Georgi Gerganov 2023-05-03 23:24:20 +03:00
  • 8dc342c069
    quick readme update CRD716 2023-05-03 15:08:02 -05:00
  • f11c0f9aa1
    add model-agnostic dan prompt CRD716 2023-05-03 15:06:24 -05:00
  • 45d94c8f6f
    ci : add cublas to windows release ci_cublas-45d94c8 Green Sky 2023-05-01 12:41:46 +02:00
  • 44286d3bc5
    ci : add cublas to windows release ci_cublas-44286d3 Green Sky 2023-05-01 12:41:46 +02:00
  • 6daa09d879
    examples : read chat prompts from a template file (#1196) khimaros 2023-05-03 10:58:11 -07:00
  • cad6ff5d36 scripts : add ppl-run-all.sh Georgi Gerganov 2023-05-03 20:53:11 +03:00
  • c2aa88189c read chat prompts from a template file khimaros 2023-04-18 14:48:23 -07:00
  • 0652b4209f
    llama : require first token to be BOS Georgi Gerganov 2023-05-03 20:25:55 +03:00
  • 3f870c55f8 quantize: make output filename optional, default to ggml-model-<ftype>.bin slaren 2023-05-03 18:43:11 +02:00
  • bca9ad938a
    minor : fix whitespaces (#1302) Georgi Gerganov 2023-05-03 20:09:42 +03:00
  • 32d8b3ff24
    minor : fix whitespaces Georgi Gerganov 2023-05-03 19:54:57 +03:00
  • f684c4d414 Merge branch 'master' of https://github.com/FSSRepo/llama.cpp FSSRepo 2023-05-03 10:47:06 -06:00
  • 197bb66339 Added readme for server example FSSRepo 2023-05-03 10:38:35 -06:00
  • 3baa706a19
    Merge branch 'ggerganov:master' into master Steward Garcia 2023-05-03 10:35:19 -06:00
  • e2a937ca6a
    minor : fix trailing whitespaces Georgi Gerganov 2023-05-03 18:43:23 +03:00
  • ede8e4edbb Merge branch 'master' into concedo_experimental Concedo 2023-05-03 23:34:50 +08:00
  • b0c71c7b6d
    scripts : platform independent script to verify sha256 checksums (#1203) KASR 2023-05-03 17:31:28 +02:00
  • a8a2efdc81
    examples : various prompt and example fixes (#1298) CRD716 2023-05-03 10:26:47 -05:00
  • 105f818d45 integrated new version of rwkv from upstream Concedo 2023-05-03 23:26:39 +08:00
  • 773455084c
    use common characters CRD716 2023-05-03 08:41:01 -05:00
  • c14ac96c2c
    miku prompt improvements CRD716 2023-05-03 08:37:24 -05:00
  • 1abe47c8d9
    fix dan.txt CRD716 2023-05-03 08:33:27 -05:00
  • 4857739ab5 allow specifying a different thread count for GPU blas Concedo 2023-05-03 21:19:59 +08:00
  • b67cc50dad
    Merge 'origin/master' into hipblas Henri Vasserman 2023-05-03 15:04:51 +03:00
  • b78af37cd2
    fix reverse prompt and multi line Tomas 2023-05-03 18:47:11 +07:00
  • 9f788b9478
    Update verify-checksum-models.py KASR 2023-05-03 13:38:49 +02:00
  • fe5d0d5a3b Update main's README.md with new features Danny Daemonic 2023-05-03 03:32:25 -07:00
  • df69e4e43e
    Merge 902075752a into e216aa0463 Amir Eslampanah 2023-05-03 10:51:59 +02:00
  • 3bdecc2aca
    Merge branch 'ggerganov:master' into master KASR 2023-05-03 08:51:58 +02:00
  • f01c6cbc7e Added httplib support FSSRepo 2023-05-02 23:55:29 -06:00
  • 89044502fe just use RT Concedo 2023-05-03 11:07:36 +08:00
  • e216aa0463
    llama : only copy used KV cache in get / set state (#1272) master-e216aa0 Evan Jones 2023-05-02 22:26:13 -04:00
  • f43a63235b priority adjustment for linux fixed Concedo 2023-05-03 10:16:43 +08:00
  • 2485d7a4d3
    Process escape sequences given in prompts (#1173) master-2485d7a DannyDaemonic 2023-05-02 18:46:20 -07:00
  • 3c249a4c74 Process escape sequences given in prompts Danny Daemonic 2023-04-25 07:39:08 -07:00
  • 13b0c68ed7
    Handle signals properly on Windows (#1123) master-13b0c68 DannyDaemonic 2023-05-02 18:01:57 -07:00
  • 55bc5f0900
    Call sh on build-info.sh (#1294) master-55bc5f0 DannyDaemonic 2023-05-02 17:52:35 -07:00
  • 9daff419f6
    fix build-info.h for git submodules (#1289) master-9daff41 kuvaus 2023-05-03 03:43:43 +03:00
  • 574f730cdb
    Merge branch 'ggerganov:master' into build_info kuvaus 2023-05-03 03:32:58 +03:00
  • da9ec4c06a Call sh on build-info.sh Danny Daemonic 2023-05-02 17:00:30 -07:00
  • 7cac587f94 fix missing parameters in llama_init_from_gpt_params (#1293) slaren 2023-05-03 01:36:45 +02:00
  • 4123652cb6 examples : add llama_init_from_gpt_params() common function (#1290) Ron Evans 2023-05-02 22:39:51 +02:00
  • 924df1a9a9 llama : fix compile warnings Georgi Gerganov 2023-05-02 23:09:08 +03:00
  • 44d4f1ed0e ggml : fix 32-bit ARM Georgi Gerganov 2023-05-02 22:14:50 +03:00
  • 3e7d5fcba0 examples : improve vertical alignment of a few variables (#1286) Ron Evans 2023-05-02 19:53:52 +02:00
  • 704c4e8c69 ggml : fix ppc64le build error and make cmake detect Power processors (#1284) Marvin Gießing 2023-05-02 18:42:16 +02:00
  • 30318b795d llama : allow 0 as a seed number. (#1275) Robert Brisita 2023-05-02 12:23:44 -04:00
  • 806cbeae2b main : switch input_noecho to input_echo to remove negation (#979) Ron Evans 2023-05-02 18:13:26 +02:00
  • bad9913de4 ggml: add names to tensors (#1268) slaren 2023-05-02 16:03:00 +02:00
  • bf4b22ffe4
    fix missing parameters in llama_init_from_gpt_params (#1293) master-bf4b22f slaren 2023-05-03 01:36:45 +02:00
  • f903cfab2a fix missing parameters in llama_init_from_gpt_params Slaren 2023-05-03 01:27:40 +02:00
  • 7dffb0da73
    make git build info work with submodules Green Sky 2023-05-03 01:17:11 +02:00
  • e06f9b86ec
    Remove custom command kuvaus 2023-05-03 01:03:36 +03:00
  • 431f1c5630
    Require .git/ to be a folder for build-info.h kuvaus 2023-05-02 22:40:44 +03:00
  • 53a87937cf Call sh on build script directly Danny Daemonic 2023-05-02 15:54:56 -07:00
  • 4aa91a230a Improve handling of buffer Danny Daemonic 2023-05-02 15:38:00 -07:00
  • fa82549c60 new/delete and fprintf Danny Daemonic 2023-05-02 08:48:36 -07:00
  • 458df7413c avoid designated initializers Evan Jones 2023-05-02 17:43:50 -04:00
  • 0bf20fe5f3 switch to ggml for copying k, v Evan Jones 2023-05-02 17:37:26 -04:00
  • 970547e71a llama : only copy used KV cache in get / set state Evan Jones 2023-05-01 23:36:31 -04:00
  • 67c77799e0
    examples : add llama_init_from_gpt_params() common function (#1290) master-67c7779 Ron Evans 2023-05-02 22:39:51 +02:00
  • a032ac5eac examples : add llama_init_from_gpt_params() common function and modify all examples to use it, in order to reduce duplicate code deadprogram 2023-05-02 21:49:28 +02:00
  • 0e6cbff1b7
    llama : fix compile warnings master-0e6cbff Georgi Gerganov 2023-05-02 23:09:08 +03:00
  • 5d5817ca60
    ggml : fix 32-bit ARM master-5d5817c Georgi Gerganov 2023-05-02 22:14:50 +03:00
  • 8c9be35ff9
    examples : improve vertical alignment of a few variables (#1286) master-8c9be35 Ron Evans 2023-05-02 19:53:52 +02:00
  • 6899e69ebc example : improve vertical alignment of a few variables deadprogram 2023-05-02 19:46:12 +02:00
  • cc0bb7235c
    ggml : fix ppc64le build error and make cmake detect Power processors (#1284) master-cc0bb72 Marvin Gießing 2023-05-02 18:42:16 +02:00
  • 2bb992f034
    llama : allow 0 as a seed number. (#1275) master-2bb992f Robert Brisita 2023-05-02 12:23:44 -04:00
  • f3e212361d
    Added support to detect ppc64* processors Marvin Gießing 2023-05-02 18:13:41 +02:00
  • e2cd506999
    main : switch input_noecho to input_echo to remove negation (#979) master-e2cd506 Ron Evans 2023-05-02 18:13:26 +02:00
  • a063f2e4d3
    Fix ppc64le build issue Marvin Gießing 2023-05-02 18:02:42 +02:00
  • 966cd2ce91 Merge remote-tracking branch 'temp/concedo' into concedo_experimental Concedo 2023-05-02 22:43:34 +08:00
  • 58f25dce86 added flag to increase processs priority Concedo 2023-05-02 22:26:55 +08:00
  • 9cdbbeeee2 Implement get_num_physical_cores() for Windows Danny Daemonic 2023-05-02 07:07:21 -07:00
  • 5d4158b12c
    Add testing to matrix Henri Vasserman 2023-05-02 16:54:28 +03:00
  • 2d099e5193
    ggml: add names to tensors (#1268) master-2d099e5 slaren 2023-05-02 16:03:00 +02:00
  • 069b3d4c37 Adds --mlock argument Sergey Kucher 2023-05-02 16:19:37 +03:00
  • 0afc2f91db check for thread support in quantize-stats John Doe 2023-05-02 08:29:13 -04:00
  • a0de04a6f1
    Add OpenBLAS support Henri Vasserman 2023-05-02 13:21:54 +03:00
  • a48eebe621
    Add OpenCL and CLBlast support Henri Vasserman 2023-05-02 00:19:10 +03:00
  • 5a10ea50da up ver Concedo 2023-05-02 18:19:08 +08:00
  • 9a9b217e57 updated embedded kobold lite with multiuser chat Concedo 2023-05-02 18:18:05 +08:00
  • b8279c82d0 When loading a safetensors file, ignore the metadata header; If no pt or pth files are available, attempt to load safetensors files ubik2 2023-05-02 02:47:35 -07:00
  • 308550b789 Adding the ability to have zero '0' as a seed number. RB 2023-05-02 04:27:30 -04:00
  • 6f702f2700 fixed stop sequence crash Concedo 2023-05-02 14:56:50 +08:00
  • 94827172e0 Merge branch 'master' into concedo Concedo 2023-05-02 14:38:31 +08:00
  • 433fa1e8b2 fix for stop sequence missing, added print for exception when loading GUI Concedo 2023-05-02 14:18:04 +08:00
  • bcc7f8b6bf Merge remote-tracking branch 'upstream/master' into eval-thread-count ml6 2023-05-01 22:05:43 -07:00
  • 14fa3d108b Handle C++ libraries without threading support. John Doe 2023-05-01 06:52:01 -04:00
  • 9af4b9e43f minor mprovements to dot file formatting Slaren 2023-05-01 23:39:53 +02:00
  • bc1c13bb66
    train with two examples, creating new tensors each time.. xaedes 2023-05-01 22:22:00 +02:00
  • fcbc262eb9
    Merge 'origin/master' into hipblas Henri Vasserman 2023-05-01 22:45:29 +03:00
  • 5f23052eb2
    switching from training with adam to lbfgs produces much better results in the baby-llama example xaedes 2023-05-01 21:01:17 +02:00
  • 29a0f8b940
    fix softmax in baby-llama example xaedes 2023-05-01 20:02:48 +02:00
  • 8fde656d24
    add baby-llama example training a very small llama model from scratch to output a sinusoidal wave. xaedes 2023-05-01 19:30:04 +02:00
  • 0703cdf2eb remove cloudflare insights Concedo 2023-05-02 00:38:10 +08:00
  • f4cef87edf
    Add git-based build information for better issue tracking (#1232) master-f4cef87 DannyDaemonic 2023-05-01 09:23:47 -07:00
  • 52151b6dac ggml: add names to tensors Slaren 2023-05-01 17:17:03 +02:00