Instructions to use Jar-ai/Water-AI-GPT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jar-ai/Water-AI-GPT2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jar-ai/Water-AI-GPT2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Jar-ai/Water-AI-GPT2") model = AutoModelForCausalLM.from_pretrained("Jar-ai/Water-AI-GPT2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Jar-ai/Water-AI-GPT2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jar-ai/Water-AI-GPT2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jar-ai/Water-AI-GPT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Jar-ai/Water-AI-GPT2
- SGLang
How to use Jar-ai/Water-AI-GPT2 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 "Jar-ai/Water-AI-GPT2" \ --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": "Jar-ai/Water-AI-GPT2", "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 "Jar-ai/Water-AI-GPT2" \ --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": "Jar-ai/Water-AI-GPT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Jar-ai/Water-AI-GPT2 with Docker Model Runner:
docker model run hf.co/Jar-ai/Water-AI-GPT2
this model only generating variations of bloop, created on www.kaggle.com. dont use in real cases
trained with Kaggle T4 x2 free
| param | value |
|---|---|
| learning_rate | 0.0005 |
| train_batch_size | 8 |
| eval_batch_size | 16 |
| seed | 42 |
| gradient_accumulation_steps | 2 |
| optimizer | AdamW |
| lr_scheduler_type | Linear |
| num_epochs | 10 |
| mixed_precision_training | native |
arch GPT-2 (LM head model) params 0.1B
| framework | version |
|---|---|
| Transformers | 5.20.2 |
| Pytorch | 2.11.0+cu130 |
| Datasets | 4.8.5 |
| Tokenizers | 0.23.3 |
- Downloads last month
- 95