Apriel 5B Base (Llamafied)

An approximate conversion of Apriel 5B Base to the Llama format.

  • No trust_remote_code required
  • Compatible w/ popular fine-tuning frameworks
  • Easier to run

Usage:

from transformers import pipeline
import torch

device = 'cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu'

pipe = pipeline('text-generation', model='mrfakename/Apriel-5B-Base-llamafied', device=device)

print(pipe('It was a dark and stormy night. The wind')[0]['generated_text'])

License: MIT (same as the original Apriel 5B model)

Downloads last month
12
Safetensors
Model size
4.83B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mrfakename/Apriel-5B-Base-llamafied

Finetuned
(3)
this model
Quantizations
2 models

Collection including mrfakename/Apriel-5B-Base-llamafied