llama.cpp
bc7b1f86 - convert : fix Llama-3_1-Nemotron-51B rope settings (#11008)

Commit

194 days ago

convert : fix Llama-3_1-Nemotron-51B rope settings (#11008) * conflict resolution * move comments after bracket to its own line * DeciLMCausalModel now reads rope_theta from config.json properly

References

#11008 - Fixed Llama-3_1-Nemotron-51B doesn't work when 4K or more tokens

Author

ymcki

Parents

6e1531ac

Files1

convert_hf_to_gguf.py

llama.cpp bc7b1f86 - convert : fix Llama-3_1-Nemotron-51B rope settings (#11008)

llama.cpp
bc7b1f86 - convert : fix Llama-3_1-Nemotron-51B rope settings (#11008)