Text Generation
ONNX Runtime GenAI
ONNX
English
Portuguese
mongodb
code
fim
autocomplete
qwen2
synthetic-data
Instructions to use esilva/KapiCoder-Mongo-Small-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ONNX Runtime GenAI
How to use esilva/KapiCoder-Mongo-Small-ONNX with ONNX Runtime GenAI:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
File size: 978 Bytes
13a42e5 | 1 2 3 4 5 6 7 8 9 10 11 | # KapiCoder-Mongo-Small v4b ONNX DML-FP16
Autocomplete FIM de MongoDB para o Kapibara Studio (1.5B, tier T1), pacote ONNX `dml-fp16` para GPU DirectML.
- Contrato de contexto: `editor-context-v2` (QwenFimPromptBuilder + cabecalho do editor com TARGET FIELDS; pos-processamento fecha os delimitadores internos), contexto 8,192 tokens, ate 128 tokens gerados, greedy.
- Paradas: `<|fim_prefix|>`, `<|fim_suffix|>`, `<|fim_middle|>`, `<|endoftext|>`, `<|im_end|>`, `<|fim_pad|>`.
- Runtime: onnxruntime-genai >= 0.15.2 (`model.type = qwen2`, adapter Qwen da IDE).
- Base: `Qwen/Qwen2.5-Coder-1.5B` @ `df3ce67c0e24480f20468b6ef2894622d69eb73b` (Apache-2.0). Dataset `v4b`. Licenca Apache-2.0 (`LICENSE`, `NOTICE.md`).
- Integridade: `kapicoder_manifest.json` (SHA-256 de cada arquivo) e `export_manifest.json` (ferramenta, comando, tamanhos).
- Estado: **candidato nao qualificado**. Medidas de paridade/latencia do Python sao PROXY; o gate oficial vem do KapiLab/harness da IDE.
|