metadata
library_name: transformers
license: apache-2.0
language:
- en
tags:
- llama-cpp
- gguf
- quantized
- smol
- tulu
base_model:
- SultanR/SmolTulu-1.7b-Instruct
pipeline_tag: text-generation
SmolTulu.GGUF
This is the GGUF version of SmolTulu-1.7b-Instruct, quantized to Q4_K_M!
Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
brew install llama.cpp
Invoke the llama.cpp server or the CLI.
CLI:
llama-cli --hf-repo SultanR/SmolTulu-1.7b-Instruct-GGUF --hf-file smoltulu-1.7b-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo SultanR/SmolTulu-1.7b-Instruct-GGUF --hf-file smoltulu-1.7b-instruct-q4_k_m.gguf -c 2048
Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
git clone https://github.com/ggerganov/llama.cpp
Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1
flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
cd llama.cpp && LLAMA_CURL=1 make
Step 3: Run inference through the main binary.
./llama-cli --hf-repo SultanR/SmolTulu-1.7b-Instruct-GGUF --hf-file smoltulu-1.7b-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo SultanR/SmolTulu-1.7b-Instruct-GGUF --hf-file smoltulu-1.7b-instruct-q4_k_m.gguf -c 2048