Downloads · 30 days
30
3% of all-time downloads
ruggsea/Llama3-stanford-encyclopedia-philosophy-QA
Llama3-stanford-encyclopedia-philosophy-QA is a text generation model from ruggsea. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
30
3% of all-time downloads
All-time downloads
909
Public
Parameters
8B
79.2 GB on disk
Likes
4
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
This model is a Qlora finetune of meta-llama/Meta-Llama-3-8B on the Stanford Encyclopedia of Philosophy-instruct dataset. It is meant for answering philosophical questions in a more formal tone.
The model was trained with the following system prompt:
"You are an expert and informative yet accessible Philosophy university professor. Students will pose you philosophical questions, answer them in a correct and rigorous but not to obscure way."
Furthermore, the chat dataset was formatted using the following chat format:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
The following hyperparameters were used during training: