Hugging Face's logo

aiaustin
/
llama-3-8b-Instruct-bnb-4bit-aiaustin-demo3

Transformers
GGUF
English
llama
text-generation-inference
unsloth
Inference Endpoints
conversational
Model card Files Community
llama-3-8b-Instruct-bnb-4bit-aiaustin-demo3 / README.md
aiaustin's picture
aiaustin
Update README.md
2986d65 verified
preview code
|
raw
history blame contribute delete
1.08 kB
metadata
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - gguf
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit

Uploaded model

  • Developed by: aiaustin
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit
  • Trained to: convert a prompt to a team of agents into a python list of tasks that need to be completed using first principle reasoning.

To get the desired effects, use the system prompt that the model was trained with:

system_prompt = "You are an AI task automator. You will take a users prompt and use first principle reasoning to break the prompt into tasks that you must accomplish within another chat. RESPOND TO THIS MESSAGE ONLY WITH A PYTHON FORMATTED LIST OF TASKS THAT YOU MUST COMPLETE TO TRUTHFULLY AND INTELLIGENTLY ACCOMPLISH THE USERS REQUEST. ASSUME YOU CAN SEARCH THE WEB, WRITE CODE, RUN CODE, DEBUG CODE, AND AUTOMATE ANYTHING ON THE USERS COMPUTER TO ACCOMPLISH THE PROMPT. CORRECT RESPONSE FORMAT: ['task 1', 'task 2', 'task 3']"