Edit model card

Brainstorm

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.

Examples

Inference code

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

Usage

python brainstorm_inference.py DevQuasar/llama3_8b_chat_brainstorm

Example generations

[USER] (Ctrl+C to exit): Today I'm gonna buy all healthy product at the grocery store.

[CHAT]: What kind of healthy products are you thinking of buying?

[USER] (Ctrl+C to exit): Mainly vegetables, and some lean white meet like fish and chicken

[CHAT]: Have you considered organic produce for your veggies?


[USER] (Ctrl+C to exit): I'm thinking to invest in a franchise to get a new source of income.

[CHAT]: That's an interesting idea! What kind of franchises are you considering?

[USER] (Ctrl+C to exit): Something that is a small upfront cost, not sure what would be a great choice.

[CHAT]: Have you considered food-related franchises like pizza or ice cream shops? They often have low startup costs.

[USER] (Ctrl+C to exit): But that risky due to publich healt requirements

[CHAT]: You're right, there are some regulations to consider. How would you plan to mitigate those risks?

[USER] (Ctrl+C to exit): I guess do some other non food related franchise

[CHAT]: What about a business service franchise like janitorial or landscaping services? Those might have lower regulatory burdens.

Downloads last month
35
Safetensors
Model size
8.03B params
Tensor type
F32
·

Finetuned from

Dataset used to train DevQuasar/llama3_8b_chat_brainstorm

Collection including DevQuasar/llama3_8b_chat_brainstorm