Skip to content
TheChatArchiveThe Chat Archive
gpt-4.1-2025-04-14· OpenAIHugging Face LMArena Human Preference 140K

what if you start off and already have opensource deepseek r1

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Hunyuanhunyuan-turbos-20250416’s answer.
  1. User

    what if you start off and already have opensource deepseek r1

  2. Assistant

    Great question! If you start with an open-source model like DeepSeek-VL-Robotics (R1), your compute requirements for building a general-purpose foundational robot can be significantly reduced—but not eliminated. Here’s a breakdown of what changes and what remains:


    What DeepSeek R1 Gives You

    • Pretrained Multi-Modal Model: DeepSeek R1 is already trained on large-scale vision-language-action data, giving you a strong base for perception, language understanding, and some action planning.
    • Open Weights: You can fine-tune or adapt the model without training from scratch.
    • Community Support: Open-source means you benefit from ongoing improvements and shared datasets.

    What You Still Need to Do

    1. Domain Adaptation / Fine-Tuning

    • Why: Your robot’s sensors, actuators, and environment will differ from DeepSeek’s training data.
    • Compute: Fine-tuning is much cheaper than pretraining. For a large model (e.g., 7B–70B parameters), expect 1,000–20,000 H100 hours depending on data size and task complexity.

    2. Simulation-to-Real Transfer

    • Why: Bridging the gap between simulated training and real-world deployment.
    • Compute: If you use simulation (e.g., Isaac Gym, MuJoCo), you’ll need 10,000–100,000 H100 hours for robust policy learning, but this is still much less than full pretraining.

    3. Reinforcement Learning / Policy Optimization

    • Why: For complex tasks (manipulation, navigation), you may need to optimize policies in simulation or with real robots.
    • Compute: 10,000–100,000 H100 hours depending on task complexity and sample efficiency.

    4. Real-World Data Collection & Fine-Tuning

    • Why: To adapt to your specific robot and environment.
    • Compute: 1,000–10,000 H100 hours for incremental updates.

    Total Compute Estimate (with DeepSeek R1 as Base)

    PhaseH100 Hours (Estimate)
    Domain Adaptation/Fine-tune1,000 – 20,000
    Sim2Real Transfer10,000 – 100,000
    RL/Policy Optimization10,000 – 100,000
    Real-World Fine-tuning1,000 – 10,000
    Total22,000 – 230,000
    • Low end: If your use case is close to DeepSeek R1’s training data and you don’t need much adaptation.
    • High end: If you need significant adaptation, new skills, or robust sim2real transfer.

    Cost Comparison

    • With DeepSeek R1: 44,000–44,000 – 460,000 (at $2/H100 hour)
    • From Scratch: 1.7M–1.7M – 17M (see previous answer)

    Key Takeaways

    • Starting with DeepSeek R1 can reduce your compute needs by 10–100x compared to training a foundational model from scratch.
    • Most of your compute will go into adaptation, not pretraining.
    • You still need significant compute for sim2real, RL, and real-world fine-tuning, but it’s much more manageable.

    If you have a specific use case or robot platform in mind, I can help you estimate even more precisely!

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.