c1c7026b47
Fix python stuff ( #109 )
1 year ago
467b149761
Refactoring `convert-pth-to-ggml.py`: more concise and readable ( #109 )
...
* 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>
1 year ago
2af23d3043
🚀 Dockerize llamacpp ( #132 )
...
* 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>
1 year ago
956dfda8ad
Use `tokenizer.vocab_size()` instead of hardcoding 32000 in convert-pth-to-ggml.py ( #142 )
...
There are ways that special tokens or other new tokens could be added to the tokenizer; therefore it's probably best not to assume the vocabulary is only 32000 tokens.
1 year ago
2a20f48efa
Fix UTF-8 handling (including colors) ( #79 )
1 year ago
7c9e54e55e
Revert "weights_only" arg - this causing more trouble than help
1 year ago
b9bd1d0141
python/pytorch compat notes ( #44 )
1 year ago
a93120236f
use weights_only in conversion script ( #32 )
...
this restricts malicious weights from executing arbitrary code by restricting the unpickler to only loading tensors, primitive types, and dictionaries
1 year ago
007a8f6f45
Support all LLaMA models + change Q4_0 quantization storage
1 year ago
70bc0b8b15
Fix a bug in the rope calculation
1 year ago
26c0846629
Initial release
1 year ago
Georgi Gerganov
qunash
Bernat Vadell
Ronsor
Val Kharitonov
Oleksandr Nikitin
deepdiffuser