Downloads · 30 days
0
distilgpt2-onion
ejjaffe/distilgpt2-onion
distilgpt2-onion is a machine learning model from ejjaffe. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Access
Public
Updated Oct 1, 2021
Repo size
1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1 GB · 100%
At a glance
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Oct 1, 2021
- SHA
- c78a34a9
Model card
From the Hugging Face model README
Load the Model
from transformers import GPT2Tokenizer, GPT2LMHeadModel
import torch
# start and end tokens for generation
START_TKN = "<|startoftext|>"
END_TKN = "<|endoftext|>"
# fine tuned on onion dataset w/ distilgpt2
tokenizer = GPT2Tokenizer.from_pretrained("distilgpt2")
model = GPT2LMHeadModel.from_pretrained("distilgpt2")
# use gpu if available
device = "cpu"
if torch.cuda.is_available():
device = "cuda"
model = model.to(device)
# get 70th epoch (decent results)
epoch = 70
modelpath = f'distilgpt2_onion_{epoch}.pt'
# load model
model.load_state_dict(torch.load(modelpath))
- Created
- Mar 2, 2022
- Updated
- Oct 1, 2021