large-language-leonid/tern-124M-code-generator

tinycode-generator

Accepted TinyCode model, based on Tern 124M. English request -> short plan -> Python code. Uses lossless whitespace-separated GPT-2 BPE.

Files

• model.onnx: complete FP32 browser inference graph, no external tensor files.
• manifest.json: SHA-256, graph dimensions and inference settings.
• checkpoint.pt: native PyTorch model (custom Tern architecture, not Transformers AutoModel).
• runtime/codenarrator/: Python architecture, tokenizer, preprocessing and decoding implementation.
• gpt2.tiktoken: complete GPT-2 mergeable token ranks (base64 token + rank).
• tinycode_config.json: architecture and task settings.

Upload ALL contents of this folder to the ROOT of a public Hugging Face model repository. Keep filenames unchanged. The website downloads model.onnx using https://huggingface.co/USERNAME/REPO/resolve/main/model.onnx. The native checkpoints are provided for reproducibility; they are not downloaded by the website. No hosted inference server is needed. Weights execute on the visitor's CPU via ONNX Runtime Web.

Reasoning is supervised generated text, not a correctness guarantee. This custom model is not directly compatible with the Hugging Face inference widget. Original pretraining model: https://huggingface.co/mikahniehaus/Tern . Consult its terms and the original sources before redistribution under another license.