Quick start

from ctransformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("npvinHnivqn/GGUF-metamath-llemma", 
                                                   model_file="metamath-llemma.gguf", 
                                                   model_type="llama", gpu_layers=0,
                                                   context_length=768)
model('''AI will ''', temperature=0.1)

Downloads last month: 2

GGUF

Model size

6.74B params

Architecture

llama

Hardware compatibility

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support