Instructions to use 71821Nikki/TrumpGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 71821Nikki/TrumpGeneration with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="71821Nikki/TrumpGeneration")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("71821Nikki/TrumpGeneration")
model = AutoModelForCausalLM.from_pretrained("71821Nikki/TrumpGeneration")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use 71821Nikki/TrumpGeneration with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "71821Nikki/TrumpGeneration"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "71821Nikki/TrumpGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/71821Nikki/TrumpGeneration

SGLang

How to use 71821Nikki/TrumpGeneration with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "71821Nikki/TrumpGeneration" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "71821Nikki/TrumpGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "71821Nikki/TrumpGeneration" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "71821Nikki/TrumpGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use 71821Nikki/TrumpGeneration with Docker Model Runner:
```
docker model run hf.co/71821Nikki/TrumpGeneration
```

71821Nikki commited on Apr 8, 2025

Commit

567f8b3

verified ·

1 Parent(s): a7e528c

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -12

README.md CHANGED Viewed

@@ -1,3 +1,16 @@
 # 🧠 TrumpGeneration
 **TrumpGeneration** is a fine-tuned version of OpenAI's GPT-2, trained on the speeches of **Donald J. Trump**. This model is designed to generate text in Trump's distinctive rhetorical style — bold, direct, and uniquely expressive.
@@ -57,15 +70,4 @@ This model may generate biased, exaggerated, or politically charged content. It
 - Built using Hugging Face Transformers
 - Base model: OpenAI GPT-2
-- Trained and released by [@71821Nikki](https://huggingface.co/71821Nikki)
----
-```
----
-license: mit
-base_model:
-- openai-community/gpt2
-pipeline_tag: text-generation
-library_name: transformers
----

+---
+license: mit
+base_model:
+- openai-community/gpt2
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- text-generation-inference
+- geopolitics
+- speech
+- Trump
+---
 # 🧠 TrumpGeneration
 **TrumpGeneration** is a fine-tuned version of OpenAI's GPT-2, trained on the speeches of **Donald J. Trump**. This model is designed to generate text in Trump's distinctive rhetorical style — bold, direct, and uniquely expressive.
 - Built using Hugging Face Transformers
 - Base model: OpenAI GPT-2
+- Trained and released by [@71821Nikki](https://huggingface.co/71821Nikki)