• @[email protected]
    link
    fedilink
    English
    17
    edit-2
    6 days ago

    DeepSeek the self-hosted model is pretty decent even as distilled down to 8b, but I always ensure i get an abliterated version to remove all the Chinese censorship (and also built-in OpenAI censorship given the actual history of how the model was actually developed).

    • @MajinBlayze
      link
      English
      56 days ago

      To be clear, that only removes (or attempts to remove) refusals; it doesn’t add in training data that it doesn’t have. Ask it about tiennemen square, for example.

      • @[email protected]
        link
        fedilink
        English
        76 days ago

        The abliterated model of DeepSeek can fully discuss Tiananmen Square. I’ve tried to even use the 4chan copy paste that allegedly gets Chinese chat users session dropped and the prompts work fine

    • @UndulyUnruly
      link
      English
      46 days ago

      ensure i get an abliterated version

      Could you expand on this re how, please and thank you.

        • @hummingbird
          link
          English
          26 days ago

          Learned something new. Thank you!

            • @[email protected]
              link
              fedilink
              English
              16 days ago

              I’m doing that with docker compose in my homelab, it’s pretty neat!

              services:
                ollama:
                  volumes:
                    - /etc/ollama-docker/ollama:/root/.ollama
                  container_name: ollama
                  pull_policy: always
                  tty: true
                  restart: unless-stopped
                  image: ollama/ollama
                  ports:
                    - 11434:11434
                  deploy:
                    resources:
                      reservations:
                        devices:
                          - driver: nvidia
                            device_ids: ['0']
                            capabilities:
                              - gpu
              
                open-webui:
                  build:
                    context: .
                    args:
                      OLLAMA_BASE_URL: '/ollama'
                    dockerfile: Dockerfile
                  image: ghcr.io/open-webui/open-webui:main
                  container_name: open-webui
                  volumes:
                    - /etc/ollama-docker/open-webui:/app/backend/data
                  depends_on:
                    - ollama
                  ports:
                    - 3000:8080
                  environment:
                    - 'OLLAMA_BASE_URL=http://ollama:11434/'
                    - 'WEBUI_SECRET_KEY='
                  extra_hosts:
                    - host.docker.internal:host-gateway
                  restart: unless-stopped
              
              volumes:
                ollama: {}
                open-webui: {}