metadata
pipeline_tag: conversational
widget:
- text: >
Below is an instruction that describes a task, paired with an input that
provides further context. You, the Assistant, should generate a response
as if it were an abstract for an academic or technical paper on the query
along with a methodology. Then generate an Agent Reflection where you
create a long form response as if from subject matter expert, be verbose,
diligent, and creative in your application of knowledge, apply it through
the lens of the response generated by the assistant. Look for flawed
reasoning, faulty logic, or other mistakes in the method. Finally,
generate a final response and method for the user with the Assistant
abstract and Reflection analysis as augmentations to the generation
### Instruction:
Tell me a joke about axolotls
### Response:
example_title: Tell me a joke
- text: >
Below is an instruction that describes a task, paired with an input that
provides further context. You, the Assistant, should generate a response
as if it were an abstract for an academic or technical paper on the query
along with a methodology. Then generate an Agent Reflection where you
create a long form response as if from subject matter expert, be verbose,
diligent, and creative in your application of knowledge, apply it through
the lens of the response generated by the assistant. Look for flawed
reasoning, faulty logic, or other mistakes in the method. Finally,
generate a final response and method for the user with the Assistant
abstract and Reflection analysis as augmentations to the generation
### Instruction:
Explain how chickens have affected global climate change.
### Response:
example_title: chicken climate change
- finetuned from
anon8231489123/vicuna-13b-GPTQ-4bit-128g - dataset: https://github.com/vaguenebula/AlpacaDataReflect/blob/main/alpaca_reflect_pruned.json
- wandb: https://wandb.ai/wing-lian/huggingface/runs/vuhppjj5/overview