Downloads · 30 days
5
25% of all-time downloads
muskuskus/moeut
moeut is a machine learning model from muskuskus. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
A moeut language model trained on filtered C4 (step 100000).
Downloads · 30 days
5
25% of all-time downloads
All-time downloads
20
Public
Parameters
37.9M
152 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors152 MB · 100%
From the Hugging Face model README
A moeut language model trained on filtered C4 (step 100000).
Custom architecture — not a transformers class. To load:
import torch
from safetensors.torch import load_file
from models.moeut import MoEUT
model = MoEUT()
model.load_state_dict(load_file('model.safetensors'), strict=False)
(strict=False because the tied lm_head weight is deduped on upload.)
Tokenizer: SentencePiece BPE, 8k vocab (c4_bpe8k.model).