Instructions to use saltacc/RandomPrompt-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use saltacc/RandomPrompt-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="saltacc/RandomPrompt-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("saltacc/RandomPrompt-v1") model = AutoModelForCausalLM.from_pretrained("saltacc/RandomPrompt-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use saltacc/RandomPrompt-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "saltacc/RandomPrompt-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saltacc/RandomPrompt-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/saltacc/RandomPrompt-v1
- SGLang
How to use saltacc/RandomPrompt-v1 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 "saltacc/RandomPrompt-v1" \ --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": "saltacc/RandomPrompt-v1", "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 "saltacc/RandomPrompt-v1" \ --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": "saltacc/RandomPrompt-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use saltacc/RandomPrompt-v1 with Docker Model Runner:
docker model run hf.co/saltacc/RandomPrompt-v1
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
# RandomPrompt-v1
|
| 6 |
+
|
| 7 |
+
A fine tuned GPT-neo 125M
|
| 8 |
+
|
| 9 |
+
The purpose of this model is to autocomplete or generate danbooru-like prompts for generating images in Stable Diffusion derivatives that use danbooru tags for text conditioning.
|
| 10 |
+
|
| 11 |
+
## Usage
|
| 12 |
+
|
| 13 |
+
### Autocompletion
|
| 14 |
+
|
| 15 |
+
Type in a few tags, and it will generate a completion of the prompt
|
| 16 |
+
|
| 17 |
+
### Generation
|
| 18 |
+
|
| 19 |
+
Type in nothing, and it will generate a prompt
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
## Training
|
| 23 |
+
|
| 24 |
+
Trained on 400k tags from danbooru posts for 600k steps, or around 0.25 epochs
|
| 25 |
+
|
| 26 |
+
https://wandb.ai/saltacc/RandomPrompt/runs/2v2arf0u?workspace=user-saltacc
|
| 27 |
+
|
| 28 |
+
I plan on doing further runs on better hardware to try to get more accurate prompt completion
|
| 29 |
+
|