aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2023-03-21fix typo in comment (#318)Mack Straight
2023-03-21Makefile: slightly cleanup for Mac Intel; echo instead of run ./main -h (#335)Qingyou Meng
2023-03-21cmdline option for custom amount of model parts (--n_parts N) (#348)anzz1
* cmdline option for custom amount of model parts (--n_parts N) * Update main.cpp --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-21Update IPFS links to quantized alpaca with new tokenizer format (#352)Kevin Kwok
2023-03-21Change default repeat_penalty to 1.0Georgi Gerganov
I feel this penalty is not really helping. Especially for the example from the README it makes results pretty bad
2023-03-21Add tokenizer test + revert to C++11 (#355)Georgi Gerganov
* Add test-tokenizer-0 to do a few tokenizations - feel free to expand * Added option to convert-pth-to-ggml.py script to dump just the vocabulary * Added ./models/ggml-vocab.bin containing just LLaMA vocab data (used for tests) * Added utility to load vocabulary file from previous point (temporary implementation) * Avoid using std::string_view and drop back to C++11 (hope I didn't break something) * Rename gpt_vocab -> llama_vocab * All CMake binaries go into ./bin/ now
2023-03-21Add initial AVX512 support for dot product on Linux (#320)Casey Primozic
* Update Makefile to detect AVX512 support and add compiler flags if it's available * Based on existing AVX2 implementation, dot product on one 32-value block of 4-bit quantized ints at a time * Perform 8 bit -> 16 bit sign extension and multiply+add on 32 values at time instead of 16 * Use built-in AVX512 horizontal reduce add to get sum at the end * Manual unrolling on inner dot product loop to reduce loop counter overhead
2023-03-21Adding missing features of CMakeLists.txt & Refactoring (#131)nusu-github
* Functionality addition CMakeLists.txt Refactoring: 1. Simplify more options that are negation of negation. LLAMA_NO_ACCELERATE -> LLAMA_ACCELERATE 2. Changed to an optional expression instead of forcing to enable AVX2 in MSVC. 3. Make CMAKE_CXX_STANDARD, which is different from Makefile, the same. 4. Use add_compile_options instead of adding options to CMAKE_C_FLAGS. 5. Make utils use target_link_libraries instead of directly referencing code. Added features: 1. Added some options. LLAMA_STATIC_LINK,LLAMA_NATIVE,LLAMA_LTO,LLAMA_GPROF,LLAMA_OPENBLAS * Fix Accelerate link in CMake * Windows build Fix * C++11 to C++17 * Reflects C/C++ standard individually * Change the version to 3.12 --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-20Nix flake: set meta.mainProgram to llamaBen Siraphob
2023-03-20Fixed tokenizer.model not found error when model dir is symlink (#325)Qingyou Meng
2023-03-20move file magic/version to header, print expected version (#319)Mack Straight
2023-03-20Docker - Fix publish docker image in GitHub Registry (#235)Bernat Vadell
* fix publish permission * try to fix docker pipeline using as password github_token & username repository_owner
2023-03-20sentencepiece bpe compatible tokenizer (#252)Mack Straight
* potential out of bounds read * fix quantize * style * Update convert-pth-to-ggml.py * mild cleanup * don't need the space-prefixing here rn since main.cpp already does it * new file magic + version header field * readme notice * missing newlines Co-authored-by: slaren <2141330+slaren@users.noreply.github.com>
2023-03-20Add tqdm to Python requirements (#293)Stephan Walter
* Add tqdm to Python requirements * Remove torchvision torchaudio, add requests
2023-03-19bugfix: default should not be interactive (#304)cocktailpeanut
2023-03-19Rename scriptGeorgi Gerganov
2023-03-19Add temporary helper script for Alpaca chatGeorgi Gerganov
2023-03-19fix coloring of last `n_batch` of prompt, and refactor line input (#221)Rickey Bowers Jr
* fix coloring of last `n_batch` of prompt, and refactor line input * forgot the newline that needs to be sent to the model * (per #283) try to force flush of color reset in SIGINT handler
2023-03-19Support for multiple reverse prompts. (#299)tjohnman
Co-authored-by: Johnman <> Co-authored-by: Johnman <tjohnman@github>
2023-03-19Improved quantize script (#222)Suaj Carrot
* Improved quantize script I improved the quantize script by adding error handling and allowing to select many models for quantization at once in the command line. I also converted it to Python for generalization as well as extensibility. * Fixes and improvements based on Matt's observations Fixed and improved many things in the script based on the reviews made by @mattsta. The parallelization suggestion is still to be revised, but code for it was still added (commented). * Small fixes to the previous commit * Corrected to use the original glob pattern The original Bash script uses a glob pattern to match files that have endings such as ...bin.0, ...bin.1, etc. That has been translated correctly to Python now. * Added support for Windows and updated README to use this script New code to set the name of the quantize script binary depending on the platform has been added (quantize.exe if working on Windows) and the README.md file has been updated to use this script instead of the Bash one. * Fixed a typo and removed shell=True in the subprocess.run call Fixed a typo regarding the new filenames of the quantized models and removed the shell=True parameter in the subprocess.run call as it was conflicting with the list of parameters. * Corrected previous commit * Small tweak: changed the name of the program in argparse This was making the automatic help message to be suggesting the program's usage as being literally "$ Quantization Script [arguments]". It should now be something like "$ python3 quantize.py [arguments]".
2023-03-19Make prompt randomization optional. (#300)tjohnman
Co-authored-by: Johnman <>
2023-03-19Respect the maximum number of tokens in interactive. (#298)tjohnman
Co-authored-by: Johnman <johnman@github> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-19Add --ignore-eos parameter (#181)slaren
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-19interactive mode: print '\n' in sigint_handler, this flush stdout thus ↵Qingyou Meng
ensure color reset. (#283)
2023-03-19Command line switch to use F16 for memory_k and memory_v (refactor of #154) ↵Erik Scholz
(#294) * Use F16 for memory_k and memory_v * add command line switch to use f16 instead of f32 for memory k+v --------- Co-authored-by: Ty Everett <ty@tyweb.us>
2023-03-19Update hot topics to mention Alpaca supportGeorgi Gerganov
2023-03-19Fix off-by-one bug (#115)Georgi Gerganov
2023-03-19Fix python stuff (#109)Georgi Gerganov
2023-03-19Refactoring `convert-pth-to-ggml.py`: more concise and readable (#109)qunash
* Refactor get_n_parts function to simplify code and improve readability * Use f-strings instead of concatenation * Refactoring: more concise and readable * modularize --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-19Drop trailing new line from file prompts (#80)Georgi Gerganov
2023-03-19Add instruction for using Alpaca (#240)Georgi Gerganov
2023-03-19Add "--instruct" argument for usage with Alpaca (#240)Georgi Gerganov
Also start adding prompts in "./prompts"
2023-03-19Change RMSNorm eps to 1e-6 (#173)Georgi Gerganov
I think this is what is used in the Python code
2023-03-18Warn user if a context size greater than 2048 tokens is specified (#274)Ronsor
LLaMA doesn't support more than 2048 token context sizes, and going above that produces terrible results.
2023-03-18Fix typo in readmePavol Rusnak
2023-03-18Add note about Python 3.11 to readmePavol Rusnak
2023-03-18Add memory/disk requirements to readmePavol Rusnak
2023-03-18Remove unused code since n_vocab is model.hparams.n_vocab (#262)Alex Nguyen
2023-03-18fixed warning with std::ignore about unused function result (#151)Justin Suess
fixed warning with std::ignore about unused function result
2023-03-18Fix n^2 loop in tokenization (#254)Gary Linscott
This causes long prompts to parse very slowly.
2023-03-18CI Improvements (#230)anzz1
* CI Improvements Manual build feature, autoreleases for Windows * better CI naming convention use branch name in releases and tags
2023-03-17Nix flake (#40)Niklas Korz
* Nix flake * Nix: only add Accelerate framework on macOS * Nix: development shel, direnv and compatibility * Nix: use python packages supplied by withPackages * Nix: remove channel compatibility * Nix: fix ARM neon dotproduct on macOS --------- Co-authored-by: Pavol Rusnak <pavol@rusnak.io>
2023-03-17Implement non-greedy tokenizer that tries to maximize token lengths (#242)thement
* Implement non-greedy tokenizer that tries to maximize token lengths * Insert single space in front of the prompt - this is to match original llama tokenizer behavior --------- Co-authored-by: Jakub Horak <jakub.horak@ibawizard.net>
2023-03-17Default to 4 threads (#243)Georgi Gerganov
2023-03-17Update Contributing sectionGeorgi Gerganov
2023-03-17Don't tell users to use a bad number of threads (#243)Stephan Walter
The readme tells people to use the command line option "-t 8", causing 8 threads to be started. On systems with fewer than 8 cores, this causes a significant slowdown. Remove the option from the example command lines and use /proc/cpuinfo on Linux to determine a sensible default.
2023-03-17add ptread link to fix cmake build under linux (#114)mmyjona
* add ptread link to fix cmake build under linux * add cmake to linux and macos platform * separate make and cmake workflow --------- Co-authored-by: Sebastián A <sebastian.aedo29@gmail.com>
2023-03-17🚀 Dockerize llamacpp (#132)Bernat Vadell
* feat: dockerize llamacpp * feat: split build & runtime stages * split dockerfile into main & tools * add quantize into tool docker image * Update .devops/tools.sh Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * add docker action pipeline * change CI to publish at github docker registry * fix name runs-on macOS-latest is macos-latest (lowercase) * include docker versioned images * fix github action docker * fix docker.yml * feat: include all-in-one command tool & update readme.md --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-17Q4_1 quantization (#193)Matvey Soloviev
* Add AVX2 version of ggml_vec_dot_q4_1 * Small optimisations to q4_1 dot product (@Const-me) * Rearrange Q4_1 quantization to work for multipart models. (Fix #152) * Fix ggml_vec_mad_q4_1 too * Fix non-vectorised q4_1 vec mul
2023-03-16Update README.mdGeorgi Gerganov
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-18 18:20:42 +0000