gguf 0.1.1 copy "gguf: ^0.1.1" to clipboard
gguf: ^0.1.1 copied to clipboard

GGUF file parser (to support getting information from LLM models to be run with llama.cpp)

Changelog #

0.1.1 #

  • Populate the calculated-value Tensor.length.
  • Calculates the layour block count using standard tensor names.

0.1.0 #

  • Initial version.
0
likes
160
points
22
downloads

Publisher

unverified uploader

Weekly Downloads

GGUF file parser (to support getting information from LLM models to be run with llama.cpp)

Repository (GitHub)
View/report issues

Topics

#gguf #llamacpp #llama-cpp #llm

Documentation

API reference

License

BSD-3-Clause (license)

Dependencies

json_annotation

More

Packages that depend on gguf