Is it working?

#1
by thyarles - opened

./cpp/main -m model/ggml-LLaMa-65B-q4_0.bin -n -1 -t 32 -c 2048 --temp 0.7 --repeat_penalty 1.2 --mirostat 2 --interactive-first --color

Log start
main: build = 1231 (769266a)
main: seed = 1694728814
gguf_init_from_file: invalid magic number 67676a74
error loading model: llama_model_loader: failed to load model from model/ggml-LLaMa-65B-q4_0.bin

llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model 'model/ggml-LLaMa-65B-q4_0.bin'
main: error: unable to load model

sha256sum model/ggml-LLaMa-65B-q4_0.bin

b11db4cfdc2371a0a1084669f499735aa7ceb779d581270395bc45752004deeb model/ggml-LLaMa-65B-q4_0.bin

This model is out of date, and isn't in the modern GGUF format. At some point I may requantize it, but there are other options out there to download from.

Sign up or log in to comment