---
title: nanochat-d32
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/nanochat-d32"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/nanochat-d32.md"
repository: AI-ModelScope/nanochat-d32
last_updated: 2025-10-20
license: mit
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 96
stars: 0
---

# nanochat-d32

> nanochat-d32 - AI-ModelScope 在 ModelScope 开源的模型。The nanochat-d32 model described in detail here.

AI-ModelScope/nanochat-d32 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可。

- **Repository**: AI-ModelScope/nanochat-d32
- **License**: mit
- **Downloads**: 96
- **Stars**: 0
- **Last updated**: 2025-10-20

Source: https://www.modelscope.cn/models/AI-ModelScope/nanochat-d32

---

The nanochat-d32 model described in detail [here](https://github.com/karpathy/nanochat/discussions/8).

I'm sorry this is a janky upload but you have to place these files correctly on your end:

  - the token_bytes.pt, tokenizer.pkl have to go into ~/.cache/nanochat/tokenizer directory
  - the meta_000650.json, model_000650.pt have to go into ~/.cache/nanochat/chatsft_checkpoints/d32/

I'll figure out how to make this less janky in the future, and to make nanochat play nicer with huggingface infra.