Instructions to use vistagi/gpt2-large-tldr-sum-rlhf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vistagi/gpt2-large-tldr-sum-rlhf with Transformers:

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

pipe = pipeline("text-generation", model="vistagi/gpt2-large-tldr-sum-rlhf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("vistagi/gpt2-large-tldr-sum-rlhf")
model = AutoModelForMultimodalLM.from_pretrained("vistagi/gpt2-large-tldr-sum-rlhf")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vistagi/gpt2-large-tldr-sum-rlhf with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/vistagi/gpt2-large-tldr-sum-rlhf

SGLang

How to use vistagi/gpt2-large-tldr-sum-rlhf 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 "vistagi/gpt2-large-tldr-sum-rlhf" \
    --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": "vistagi/gpt2-large-tldr-sum-rlhf",
		"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 "vistagi/gpt2-large-tldr-sum-rlhf" \
        --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": "vistagi/gpt2-large-tldr-sum-rlhf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vistagi/gpt2-large-tldr-sum-rlhf with Docker Model Runner:
```
docker model run hf.co/vistagi/gpt2-large-tldr-sum-rlhf
```

GPT-2 Large RLHF Model for OpenAI TLDR Summarization

Based on SFT model ellipseai/gpt2-large-tldr-sum and perform RLHF training for better human alignment. The training curve on validation reward is

We perform evaluation for SFT model and RL model on 386 test set on the summarization quality with Claude-v2 to judge winner. We observe that RL model is significantly better than SFT model. This demonstrate that RL training is work very well.

model	win	loss	tie	win rate	loss rate	win rate adjusted
ellipseai/gpt2-large-tldr-sum	24	151	211	0.0622	0.3911	33.55%
ellipseai/gpt2-large-tldr-sum-rlhf	151	24	211	0.3911	0.0622	66.45%

Downloads last month: 2