Grupo-Parquet-ITESO/recipe-llm-gguf
19
recipe-llm-gguf
TinyLlama-1.1B-Chat fine-tuned with LoRA for recipe generation. Quantized to Q4KM GGUF for CPU inference with llama-cpp-python.
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="Grupo-Parquet-ITESO/recipe-llm-gguf",
filename="tinyllama-recipes-q4.gguf",
)