Instructions to use Saif-M/PokeBrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Saif-M/PokeBrain with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Saif-M/PokeBrain")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Saif-M/PokeBrain") model = AutoModelForCausalLM.from_pretrained("Saif-M/PokeBrain") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Saif-M/PokeBrain with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Saif-M/PokeBrain" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Saif-M/PokeBrain", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Saif-M/PokeBrain
- SGLang
How to use Saif-M/PokeBrain 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 "Saif-M/PokeBrain" \ --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": "Saif-M/PokeBrain", "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 "Saif-M/PokeBrain" \ --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": "Saif-M/PokeBrain", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Saif-M/PokeBrain with Docker Model Runner:
docker model run hf.co/Saif-M/PokeBrain
PokeBrain Model
PokeBrain is a fine-tuned model based on the GPT-2 XL architecture. It has been trained on the dataset Saif-M/Pokemon_Data and further fine-tuned on the pre-trained GPT-2 XL model. This model is developed by Saif Mahammed, an Artificial Intelligence enthusiast and an intern at Dignity of Nobel. The fine-tuning process took approximately 12 to 16 hours.
License
This model is licensed under AFL-3.0.
Contact Information
For inquiries and collaborations, you can reach out to Saif Mahammed via email at fivestromcode@gmail.com. Check out Saif's portfolio here.
- Downloads last month
- -
Dataset used to train Saif-M/PokeBrain
Viewer • Updated • 1.07k • 6 • 1
# Gated model: Login with a HF token with gated access permission hf auth login