Downloads · 30 days
0
grqphical07/gemma-3-1b-trump
gemma-3-1b-trump is a machine learning model from grqphical07. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
I took gemma-3b-it and trained it on a dataset of Donald Trump's TruthSocial posts to make it respond in language similar to how Donald Trump would. This repo contains a script that scrapes TruthSocial for the data us…
Downloads · 30 days
0
Access
Public
Updated Nov 26, 2025
Repo size
3 MB
Likes
0
Public
Click a slice to open those files.
.safetensors3 MB · 100%
From the Hugging Face model README
I took gemma-3b-it and trained it on a dataset of Donald Trump's TruthSocial posts to make it respond in language similar to how Donald Trump would. This repo contains a script that scrapes TruthSocial for the data used to fine tune this model
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("grqphical07/gemma-3-1b-trump", device_map="auto", offload_folder="offload_model_weights", torch_dtype=torch.float16)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-3-1b-it")
model_inputs = tokenizer("What are your thoughts on ice cream?", return_tensors="pt").to(model.device)
generated_ids = model.generate(**model_inputs, max_new_tokens=200)
print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0])
TrumpLLM is licensed under the MIT License