Instructions to use migueldeguzmandev/GPT2XL-RLLM-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use migueldeguzmandev/GPT2XL-RLLM-2 with Transformers:

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

pipe = pipeline("text-generation", model="migueldeguzmandev/GPT2XL-RLLM-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("migueldeguzmandev/GPT2XL-RLLM-2")
model = AutoModelForCausalLM.from_pretrained("migueldeguzmandev/GPT2XL-RLLM-2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use migueldeguzmandev/GPT2XL-RLLM-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "migueldeguzmandev/GPT2XL-RLLM-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "migueldeguzmandev/GPT2XL-RLLM-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/migueldeguzmandev/GPT2XL-RLLM-2

SGLang

How to use migueldeguzmandev/GPT2XL-RLLM-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 "migueldeguzmandev/GPT2XL-RLLM-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": "migueldeguzmandev/GPT2XL-RLLM-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 "migueldeguzmandev/GPT2XL-RLLM-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": "migueldeguzmandev/GPT2XL-RLLM-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use migueldeguzmandev/GPT2XL-RLLM-2 with Docker Model Runner:
```
docker model run hf.co/migueldeguzmandev/GPT2XL-RLLM-2
```

migueldeguzmandev commited on Apr 18, 2024

Commit

a554f2c

verified ·

1 Parent(s): a7a56af

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -1,3 +1,3 @@
-**Repository for GPT2XL-RLFC-2 Model; feel free to use / download the files for research purposes.**
-**Related post:** [RL for safety work or just clever RL? Reinforcement Learning from Framework Continuums (RLFC)](https://www.lesswrong.com/posts/GrxaMeekGKK6WKwmm/rl-for-safety-work-or-just-clever-rl-reinforcement-learning?utm_campaign=post_share&utm_source=link)


1	+ Repository for GPT2XL-RLLM-2 Model; feel free to use / download the files for research purposes.
2
3	+ Related post: [Reinforcement Learning using Layered Morphology (RLLM)](https://www.lesswrong.com/posts/GrxaMeekGKK6WKwmm/rl-for-safety-work-or-just-clever-rl-reinforcement-learning?utm_campaign=post_share&utm_source=link)