Instructions to use dejanseo/reverse-prompter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dejanseo/reverse-prompter with Transformers:

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

pipe = pipeline("text-generation", model="dejanseo/reverse-prompter")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dejanseo/reverse-prompter")
model = AutoModelForCausalLM.from_pretrained("dejanseo/reverse-prompter")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dejanseo/reverse-prompter with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dejanseo/reverse-prompter

SGLang

How to use dejanseo/reverse-prompter 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 "dejanseo/reverse-prompter" \
    --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": "dejanseo/reverse-prompter",
		"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 "dejanseo/reverse-prompter" \
        --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": "dejanseo/reverse-prompter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dejanseo/reverse-prompter with Docker Model Runner:
```
docker model run hf.co/dejanseo/reverse-prompter
```

dejanseo commited on Mar 18

Commit

6a57787

verified ·

1 Parent(s): eeb56d0

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -87,6 +87,9 @@ Prompt-response pairs were formatted as `{response}\n###\n{prompt}<eos>` and tok
 | Warmup steps | 100 |
 | Max sequence length | 2048 |
 | Gradient checkpointing | Enabled |
 ## Inference Strategy

 | Warmup steps | 100 |
 | Max sequence length | 2048 |
 | Gradient checkpointing | Enabled |
+| GPU | NVIDIA GeForce RTX 4090 (24 GB) |
+| CPU | AMD Ryzen 9 7950X3D 16-Core |
+| RAM | 64 GB |
 ## Inference Strategy