The 1 GB build of Nock Coder v2.1 (Nock-AI/nock-coder-1.5b-v2.1): an open coding model from NockAI that answers with the code first. One 986 MB file, Q4KM, for Ollama and llama.cpp on Windows, macOS and Linux. No GPU, account or API key needed. Measured on this exact file with Ollama: temperature 0, fixed seed, each model with its own default system prompt, on a Kaggle T4 (October 11, 2026). v2.1 trains the v2 data more gently (1 epoch at learning rate 1e-4 instead of 2 epochs at 2e-4) and passes 6 more HumanEval problems than the base model while keeping the code first habit. The v2 file is still in this repo’s history. Compiling is a low bar: it says nothing about whether a contract is correct or safe. — This is a 1.5B model. It makes mistakes, and its code can be wrong or insecure. Review it before you run it. — Smart contract output is not audited. Have contracts reviewed by a qualified person before you deploy them. — NockAI is an independent project and is not affiliated with Robinhood, Alibaba or Nockchain.
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат
Задача: Генерация текста
Автор: Nock-AI
Теги: gguf, code, solidity, ollama, endpoints_compatible, conversational
Лайков: 3 | Загрузок: 624
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
