Issue: HuggingFace Documentation Refers to Outdated Binaries #8659
Description
What happened?
This isn't a problem that we control, but if someone knows who to contact at Hugging Face, then it would be good to get the llama.cpp instructions from the "Use This Model" button to refer to the updated binary names from #7809 .
Example:
From a GGUF'd model page (such as this one), click "Use This Model", then "llama.cpp", and you'll see a screen like the following:
# Option 1: use llama.cpp with brew
brew install llama.cpp
# Load and run the model
llama \
--hf-repo "QuantFactory/Mistral-Nemo-Instruct-2407-GGUF" \
--hf-file Mistral-Nemo-Instruct-2407.Q2_K.gguf \
-p "I believe the meaning of life is" \
-n 128 Copy # Option 2: build llama.cpp from source with curl support
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
LLAMA_CURL=1 make
# Load and run the model
./main \
--hf-repo "QuantFactory/Mistral-Nemo-Instruct-2407-GGUF" \
-m Mistral-Nemo-Instruct-2407.Q2_K.gguf \
-p "I believe the meaning of life is" \
-n 128
The instructions in "Option 2" should be updated to be llama-cli instead of main.
It's not a huge deal, but I looked through the HF Repositories list and it wasn't immediately obvious which one this should be reported in.
Mainly wanted to report this here so that we had a place to track it.
Name and Version
n/a
What operating system are you seeing the problem on?
No response
Relevant log output
No response