Deepseek V4 Python Packages

nemo-automodel

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

mcore-bridge

MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers — with support for 300+ large language models (Qwen3-Next, GLM-5.3, Deepseek-V4, MiniMax-2.7, ...) and 200+ multimodal large models (Qwen3.8, Qwen3-Omni, Gemma4, ...).

freetoken

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

deepseek-harness

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes included.

asicode

Autonomous Self Improvement — AST-precise coding agent with verification gates. Multi-language CLI powered by tree-sitter.

deepseek-harness-cli

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes included.

deepseek-1m

🚀 Chat with your entire codebase, book, or email archive using DeepSeek-V4's 1M token context. No RAG. No chunking. Just pure memory.

nano-deepseek-v4

A compact, readable PyTorch reference implementation of the DeepSeek-V4 architecture (Flash and Pro), in the spirit of nanoGPT. ~4,300 LOC.