26 lines
1.2 KiB
Markdown
26 lines
1.2 KiB
Markdown
---
|
|
license: llama3
|
|
datasets:
|
|
- DevQuasar/brainstorm-v2.1_vicuna_1k
|
|
pipeline_tag: text-generation
|
|
---
|
|
# Brainstorm GGUF
|
|
|
|
|
|
|
|
|
|
Quantized GGUF model files for [DevQuasar/llama3_8b_chat_brainstorm-v2.1](https://huggingface.co/DevQuasar/llama3_8b_chat_brainstorm-v2.1)
|
|
|
|
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 summaryze the discussed ideas in Markdown format.
|
|
## Usage
|
|
### LMStudio
|
|
With https://lmstudio.ai/ use the `brainstorm.preset.json` preset
|
|
|
|
### llama.cpp
|
|
`./main -m llama3_8b_chat_brainstorm-v2.1.Q2_K.gguf -p "### HUMAN: I'd like to build an online marketplace\n ### ASSISTANT:" -n 400 -e -ins -r "### HUMAN:\n" -r "### ASSISTANT: "`
|
|
|
|
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/ |