Brainstorm-v2.1

image/png

Model intention

Brainstorm facilitates idea exploration through interaction with a Language Model (LLM). Rather than providing direct answers, the model engages in a dialogue with users, offering probing questions aimed at fostering deeper contemplation and consideration of various facets of their ideas. Model can summarize the discussed ideas in Markdown format.

Examples

Inference code

https://github.com/csabakecskemeti/ai_utils/blob/main/brainstorm_inference.py

Example generations

[USER] (Ctrl+C to exit): I'd like to organize my vintage computer collection

[CHAT]: That sounds like a great idea! What kind of organization system are you thinking of using?

[USER] (Ctrl+C to exit): Make it sure that they are available for use any time, but I don't want to see all the cables hanging around

[CHAT]: So you want to make it easy to access and tidy up the cables. Have you considered using a cable management system or tying up loose ends with ribbon cutters?

[USER] (Ctrl+C to exit): That makes sense

[CHAT]: What about labeling each device so you can find what you need quickly?

[USER] (Ctrl+C to exit): Can you please summaryze what we've been talked so far?

[CHAT]: Here's a summary:

Organizing Vintage Computer Collection

  • Make sure devices are easily accessible for use
  • Tidy up cables using a cable management system or ribbon cutters
  • Label each device to find it quickly

Let me know if you'd like to add or modify anything!

[USER] (Ctrl+C to exit): Ok let's continue: I also want to use a single monoytor an pheripherias for all computer

[CHAT]: That could get expensive fast. Are you thinking of using a hub or a switch? Or maybe something more sophisticated like a KVM switch?

[USER] (Ctrl+C to exit): yest that's make sense, can you please add it to the summary?

[CHAT]: Here's the updated summary:

Organizing Vintage Computer Collection

  • Make sure devices are easily accessible for use
  • Tidy up cables using a cable management system or ribbon cutters
  • Label each device to find it quickly
  • Use a single monitor and peripherals for all computers (hub, switch, KVM switch)

Let me know if there's anything else you'd like to add or change!

[USER] (Ctrl+C to exit): I also want to protect them from dust, not sure how to do that

[CHAT]: For protecting against dust, one option could be using enclosures or cabinets. Another approach might be setting up a dedicated workspace with appropriate ventilation. Which of these ideas resonates with you?

I'm doing this to 'Make knowledge free for everyone', using my personal time and resources.

If you want to support my efforts please visit my ko-fi page: https://ko-fi.com/devquasar

Also feel free to visit my website https://devquasar.com/

Downloads last month
25
Safetensors
Model size
8.03B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for DevQuasar/llama3_8b_chat_brainstorm-v2.1

Finetuned
(373)
this model

Dataset used to train DevQuasar/llama3_8b_chat_brainstorm-v2.1

Space using DevQuasar/llama3_8b_chat_brainstorm-v2.1 1

Collection including DevQuasar/llama3_8b_chat_brainstorm-v2.1