#Trying to# Save to q4_k_m GGUFmodel.push_to_hub_gguf(FINETUNED_MODEL_NAME, tokenizer, quantization

1 messages · Page 1 of 1 (latest)

willow trail
#

I am getting RuntimeError: *** Unsloth: Failed compiling llama.cpp using os.system(...) with error 256. Please report this ASAP!

📎 message.txt 📎 message.txt
#

I had already installed brew install llama.cpp so unsloth shouldn't try to compile llama.cpp