llama.cpp
9958c81b - Implement the OLMo architecture (#6741)

Commit
1 year ago
Implement the OLMo architecture (#6741) * implement olmo architecture * remove unused variable * remove unused moe branch * remove check for weight * remove superfluous moe, bias and rope tensors * clarified comment * fix clamp_kqv setting * remove obsolete parameter name filter
Author
Parents
  • File
    README.md
  • File
    convert-hf-to-gguf.py
  • gguf-py/gguf
    • File
      constants.py
  • File
    llama.cpp