Instructions to use alainbrown/tiny-gpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alainbrown/tiny-gpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="alainbrown/tiny-gpt", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("alainbrown/tiny-gpt", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use alainbrown/tiny-gpt with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "alainbrown/tiny-gpt" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "alainbrown/tiny-gpt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/alainbrown/tiny-gpt
- SGLang
How to use alainbrown/tiny-gpt 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 "alainbrown/tiny-gpt" \ --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": "alainbrown/tiny-gpt", "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 "alainbrown/tiny-gpt" \ --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": "alainbrown/tiny-gpt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use alainbrown/tiny-gpt with Docker Model Runner:
docker model run hf.co/alainbrown/tiny-gpt
| { | |
| "architectures": [ | |
| "TinyGPTForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_tiny_gpt.TinyGPTConfig", | |
| "AutoModelForCausalLM": "modeling_tiny_gpt.TinyGPTForCausalLM" | |
| }, | |
| "context_size": 1024, | |
| "d_model": 384, | |
| "dropout": 0.0, | |
| "dtype": "float32", | |
| "eos_token_id": 0, | |
| "hidden_size": 384, | |
| "max_position_embeddings": 1024, | |
| "model_type": "tiny_gpt", | |
| "n_heads": 6, | |
| "n_layers": 10, | |
| "num_attention_heads": 6, | |
| "num_hidden_layers": 10, | |
| "pad_token_id": 0, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.12.1", | |
| "vocab_size": 16000 | |
| } | |