Downloads · 30 days
4
20% of all-time downloads
RichardErkhov/ruggsea_-_Llama3-stanford-encyclopedia-philosophy-QA-4bits
ruggsea_-_Llama3-stanford-encyclopedia-philosophy-QA-4bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
4
20% of all-time downloads
All-time downloads
20
Public
Parameters
8.1B
6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6 GB · 100%
How the weights are stored.
U87B · 86%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Llama3-stanford-encyclopedia-philosophy-QA - bnb 4bits
language:
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: