Prompt Format?
#4
by
xzuyn
- opened
Is this using the same format as the LoRA versions? https://huggingface.co./JosephusCheung/Guanaco & https://huggingface.co./KBlueLeaf/guanaco-7B-leh
LoRA Version's Format
### Instruction:
User: History User Input
Assistant: History Assistant Answer
### Input:
System: Knowledge
User: New User Input
### Response:
New Assistant Answer
Based on what @mljxy says on this discussion its not the same as your QLoRA? https://huggingface.co./TheBloke/guanaco-13B-GGML/discussions/1#646f9d3b6098ee820fbd4dba
header = "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."
prompt_template = "### Human: {query}\n### Assistant:{response}"
Could you add a readme to these QLoRA models so that it's better understood how to properly use them?
I have read the source code, the prompt should be:
A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
### Human: {input}
### Assistant: {output}
I have read the source code, the prompt should be:
A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. ### Human: {input} ### Assistant: {output}
I'm interested in how I can read the source code to a llm.
Thanks