* docs - Alternative way to build at Android, with CLBlast.
* doc - LD_LIBRARY_PATH complement for some Android devices when building with CLBlast inside Termux.
* doc- fix typo
* Convert vector to f16 for dmmv
* compile option
* Added compilation option description to README
* Changed cmake CUDA_ARCHITECTURES from "OFF" to "native"
* mtl : export the LLaMA computation graph
* ci : disable temporary
* mtl : adapt the MNIST example as starter
* mtl : no need for mtl-export tool, add cli arg for main instead
* mtl : export just a small part of the graph for now to make it easier
* mtl : move MSL code into separate file for easy editing
* mtl : initial get_rows_q4_0 kernel
* mtl : confirmed get_rows_q4_0 is working correctly
* mtl : add rms_norm kernel + confirm working
* mtl : add mul kernel + confirm working
* mtl : initial mul_mat Q4 kernel (wrong results)
* mtl : mul_mat fixes (still wrong)
* mtl : another mul_mat Q4 (still does not work)
* mtl : working mul_mat q4
* ggml : fix handling of "view" ops in ggml_graph_import()
* mtl : add rope kernel
* mtl : add reshape and transpose handling
* ggml : store offset as opt arg for ggml_view_xd() operators
* mtl : add cpy kernel + handle view ops
* mtl : confirm f16 x f32 attention mul mat
* mtl : add scale kernel
* mtl : add diag_mask_inf kernel
* mtl : fix soft_max kernel
* ggml : update ggml_nbytes() to handle non-contiguous tensors
* mtl : verify V tensor contents
* mtl : add f32 -> f32 cpy kernel
* mtl : add silu kernel
* mtl : add non-broadcast mul kernel
* mtl : full GPU inference of the computation graph
* mtl : optimize rms_norm and soft_max kernels
* mtl : add f16 mat x f32 vec multiplication kernel
* mtl : fix bug in f16 x f32 mul mat + speed-up computation
* mtl : faster mul_mat_q4_0_f32 kernel
* mtl : fix kernel signature + roll inner loop
* mtl : more threads for rms_norm + better timing
* mtl : remove printfs from inner loop
* mtl : simplify implementation
* mtl : add save/load vocab to ggml file
* mtl : plug Metal inference into llama.cpp (very quick-n-dirty)
* mtl : make it work with main example
Lots of hacks but at least now it generates text
* mtl : preparing for merge
* mtl : clean-up ggml mtl interface + suport scratch / inplace
* mtl : remove temp / debug code
* metal : final refactoring and simplification
* Revert "ci : disable temporary"
This reverts commit 98c267fc77.
* metal : add comments
* metal : clean-up stuff, fix typos
* readme : add Metal instructions
* readme : add example for main
* feature: add blis support
* feature: allow all BLA_VENDOR to be assigned in cmake arguments. align with whisper.cpp pr 927
* fix: version detection for BLA_SIZEOF_INTEGER, recover min version of cmake
* Fix typo in INTEGER
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Fix: blas changes on ci
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* feature: add blis support
* feature: allow all BLA_VENDOR to be assigned in cmake arguments. align with whisper.cpp pr 927
* fix: version detection for BLA_SIZEOF_INTEGER, recover min version of cmake
* Fix typo in INTEGER
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* python script to verify the checksum of the llama models
Added Python script for verifying SHA256 checksums of files in a directory, which can run on multiple platforms. Improved the formatting of the output results for better readability.
* Update README.md
update to the readme for improved readability and to explain the usage of the python checksum verification script
* update the verification script
I've extended the script based on suggestions by @prusnak
The script now checks the available RAM, is there is enough to check the file at once it will do so. If not the file is read in chunks.
* minor improvment
small change so that the available ram is checked and not the total ram
* remove the part of the code that reads the file at once if enough ram is available
based on suggestions from @prusnak i removed the part of the code that checks whether the user had enough ram to read the entire model at once. the file is now always read in chunks.
* Update verify-checksum-models.py
quick fix to pass the git check
* Updated build information
First update to the build instructions to include BLAS.
* Update README.md
* Update information about BLAS
* Better BLAS explanation
Adding a clearer BLAS explanation and adding a link to download the CUDA toolkit.
* Better BLAS explanation
* BLAS for Mac
Specifying that BLAS is already supported on Macs using the Accelerate Framework.
* Clarify the effect of BLAS
* Windows Make instructions
Added the instructions to build with Make on Windows
* Fixing typo
* Fix trailing whitespace
instead of `int` (while `int` option still being supported)
This allows the following usage:
`./quantize ggml-model-f16.bin ggml-model-q4_0.bin q4_0`
instead of:
`./quantize ggml-model-f16.bin ggml-model-q4_0.bin 2`
Current status: Working, except for the latest GPTQ-for-LLaMa format
that includes `g_idx`. This turns out to require changes to GGML, so
for now it only works if you use the `--outtype` option to dequantize it
back to f16 (which is pointless except for debugging).
I also included some cleanup for the C++ code.
This script is meant to replace all the existing conversion scripts
(including the ones that convert from older GGML formats), while also
adding support for some new formats. Specifically, I've tested with:
- [x] `LLaMA` (original)
- [x] `llama-65b-4bit`
- [x] `alpaca-native`
- [x] `alpaca-native-4bit`
- [x] LLaMA converted to 'transformers' format using
`convert_llama_weights_to_hf.py`
- [x] `alpaca-native` quantized with `--true-sequential --act-order
--groupsize 128` (dequantized only)
- [x] same as above plus `--save_safetensors`
- [x] GPT4All
- [x] stock unversioned ggml
- [x] ggmh
There's enough overlap in the logic needed to handle these different
cases that it seemed best to move to a single script.
I haven't tried this with Alpaca-LoRA because I don't know where to find
it.
Useful features:
- Uses multiple threads for a speedup in some cases (though the Python
GIL limits the gain, and sometimes it's disk-bound anyway).
- Combines split models into a single file (both the intra-tensor split
of the original and the inter-tensor split of 'transformers' format
files). Single files are more convenient to work with and more
friendly to future changes to use memory mapping on the C++ side. To
accomplish this without increasing memory requirements, it has some
custom loading code which avoids loading whole input files into memory
at once.
- Because of the custom loading code, it no longer depends in PyTorch,
which might make installing dependencies slightly easier or faster...
although it still depends on NumPy and sentencepiece, so I don't know
if there's any meaningful difference. In any case, I also added a
requirements.txt file to lock the dependency versions in case of any
future breaking changes.
- Type annotations checked with mypy.
- Some attempts to be extra user-friendly:
- The script tries to be forgiving with arguments, e.g. you can
specify either the model file itself or the directory containing
it.
- The script doesn't depend on config.json / params.json, just in
case the user downloaded files individually and doesn't have those
handy. But you still need tokenizer.model and, for Alpaca,
added_tokens.json.
- The script tries to give a helpful error message if
added_tokens.json is missing.
* Revert "Delete SHA256SUMS for now (#416)"
This reverts commit 8eea5ae0e5.
* Remove ggml files until they can be verified
* Remove alpaca json
* Add also model/tokenizer.model to SHA256SUMS + update README
---------
Co-authored-by: Pavol Rusnak <pavol@rusnak.io>
* Update custom.md
* Removed Model section as it is better placed in README.md
* Updates to README.md model section
* Inserted text that was removed from issue template about obtaining models from FB and links to papers describing the various models
* Removed IPF down links for the Alpaca 7B models as these look to be in the old data format and probably shouldn't be directly linked to, anyway
* Updated the perplexity section to point at Perplexity scores #406 discussion
* 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>
* 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]".
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.
* Add quantize script for batch quantization
* Indentation
* README for new quantize.sh
* Fix script name
* Fix file list on Mac OS
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Initial work on interactive mode.
* Improve interactive mode. Make rev. prompt optional.
* Update README to explain interactive mode.
* Fix OS X build
