Instructions to use daspartho/prompt-extend with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use daspartho/prompt-extend with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="daspartho/prompt-extend")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("daspartho/prompt-extend") model = AutoModelForCausalLM.from_pretrained("daspartho/prompt-extend") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use daspartho/prompt-extend with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "daspartho/prompt-extend" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "daspartho/prompt-extend", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/daspartho/prompt-extend
- SGLang
How to use daspartho/prompt-extend 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 "daspartho/prompt-extend" \ --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": "daspartho/prompt-extend", "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 "daspartho/prompt-extend" \ --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": "daspartho/prompt-extend", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use daspartho/prompt-extend with Docker Model Runner:
docker model run hf.co/daspartho/prompt-extend
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,11 +12,7 @@ model-index:
|
|
| 12 |
|
| 13 |
Text generation model for generating suitable style cues given the main idea for a prompt.
|
| 14 |
|
| 15 |
-
GPT-2 model trained on [dataset](https://huggingface.co/datasets/daspartho/stable-diffusion-prompts) of stable diffusion prompts.
|
| 16 |
-
|
| 17 |
-
## Intended use
|
| 18 |
-
|
| 19 |
-
Extend stable diffusion prompts with suitable style cues.
|
| 20 |
|
| 21 |
### Training hyperparameters
|
| 22 |
|
|
|
|
| 12 |
|
| 13 |
Text generation model for generating suitable style cues given the main idea for a prompt.
|
| 14 |
|
| 15 |
+
It is a GPT-2 model trained on [dataset](https://huggingface.co/datasets/daspartho/stable-diffusion-prompts) of stable diffusion prompts.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
### Training hyperparameters
|
| 18 |
|