Skip to content

fine-tuning 2

  • dsh-unsloth v0.2.0 Verified

    Unsloth for DeepSeek Harness: local LLM fine-tuning and dataset generation. Bundles a zero-dependency Python MCP server and mounts DSH's own MCP client, exposing model inventory, Data Recipe dataset generation, LoRA/QLoRA training, GGUF export and inferen

    dsh plugin add dsh-unsloth
  • dsh-tunetune v0.8.7 Verified Web UI

    TuneTune for DeepSeek Harness: train, test, and improve small models with your Agent, with a workbench beside the conversation.

    dsh plugin add dsh-tunetune