Instructions to use pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO with Transformers:

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

pipe = pipeline("text-generation", model="pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO")
model = AutoModelForCausalLM.from_pretrained("pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO

SGLang

How to use pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO 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 "pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO" \
    --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": "pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO",
		"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 "pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO" \
        --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": "pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO with Docker Model Runner:
```
docker model run hf.co/pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO
```

GPT2-IMDB is pretrained on IMDB dataset. Aligning the model using Proximal Policy Optimization (PPO). The goal is to train the model to generate positive sentiment reviews. The training process utilizes the trl library for reinforcement learning, the transformers library for model handling, and datasets for dataset management. Implementation code is available here: GitHub

# Load model and tokenizer directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pt-sk/GPT2-IMDB-Sentiment-FineTuning-with-PPO")
model = AutoModelForCausalLM.from_pretrained("pt-sk/GPT2-IMDB-Sentiment-FineTuning-with-PPO")

# Example usage
input_text = "The movie was fantastic"
inputs = tokenizer(input_text, return_tensors='pt')
outputs = model.generate(**inputs)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 6

Safetensors

Model size

0.1B params

Tensor type

F32

pt-sk
/

GPT2-IMDB-Sentiment-FineTuned-with-PPO

Dataset used to train pt-sk/GPT2-IMDB-Sentiment-FineTuned-with-PPO