Instructions to use damerajee/gpt2-large-hist-quotes-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use damerajee/gpt2-large-hist-quotes-2 with Transformers:

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

pipe = pipeline("text-generation", model="damerajee/gpt2-large-hist-quotes-2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("damerajee/gpt2-large-hist-quotes-2")
model = AutoModelForCausalLM.from_pretrained("damerajee/gpt2-large-hist-quotes-2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use damerajee/gpt2-large-hist-quotes-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "damerajee/gpt2-large-hist-quotes-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "damerajee/gpt2-large-hist-quotes-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/damerajee/gpt2-large-hist-quotes-2

SGLang

How to use damerajee/gpt2-large-hist-quotes-2 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 "damerajee/gpt2-large-hist-quotes-2" \
    --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": "damerajee/gpt2-large-hist-quotes-2",
		"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 "damerajee/gpt2-large-hist-quotes-2" \
        --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": "damerajee/gpt2-large-hist-quotes-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use damerajee/gpt2-large-hist-quotes-2 with Docker Model Runner:
```
docker model run hf.co/damerajee/gpt2-large-hist-quotes-2
```

Model Description

This model was finetuned on the DatasetA-Roucher/english_historical_quotes using the model gpt2-large

Example Use cases


from transformers import pipeline
pipe = pipeline("text-generation", model="damerajee/gpt2-large-hist-quotes-2")
prompt = "write a quote based on business"
generated_quote = pipe(prompt,top_k=2, temperature=2.0,repetition_penalty=2.0)[0]['generated_text']
print('\n\n', generated_quote)

Streaming option


from transformers import import AutoModelForCausalLM, AutoTokenizer, TextStreamer, pipeline
streamer = TextStreamer(tokenzier, skip_prompt=True)
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenzier,
    max_length=40,
    temperature=0.6,
    pad_token_id=tokenzier.eos_token_id,
    top_p=0.95,
    repetition_penalty=1.2,
    streamer=streamer
)
pipe("write a quote based on war and business")

Downloads last month: 14

Safetensors

Model size

0.8B params

Tensor type

F16

damerajee
/

gpt2-large-hist-quotes-2

Model Description

Example Use cases

Streaming option

Dataset used to train damerajee/gpt2-large-hist-quotes-2