28 lines
713 B
Markdown
28 lines
713 B
Markdown
|
---
|
||
|
|
base_model: Qwen/Qwen3-0.6B
|
||
|
|
tags:
|
||
|
|
- peft
|
||
|
|
- lora
|
||
|
|
- text-generation
|
||
|
|
---
|
||
|
|
|
||
|
|
# Qwen3-0.6B-bible-assistant
|
||
|
|
|
||
|
|
## Model Description
|
||
|
|
Fine-tuned from `Qwen/Qwen3-0.6B` using QLoRA (4-bit) with supervised fine-tuning.
|
||
|
|
|
||
|
|
## Training Details
|
||
|
|
- Dataset: `juvereturn/bible-dataset`
|
||
|
|
- LoRA rank: 16, alpha: 32
|
||
|
|
- Epochs: 3, Learning rate: 0.0002
|
||
|
|
|
||
|
|
## Intended Use
|
||
|
|
|
||
|
|
This model is a test model used for the CS-394/594 class at DigiPen.
|
||
|
|
|
||
|
|
The model is a Bible assistant that can answer people's questions about the Bible and help them feel better. I believe the Bible has the ability to heal everyone in the world.
|
||
|
|
|
||
|
|
## Limitations
|
||
|
|
|
||
|
|
This model is a single-turn model and has not been trained on support long, multi-turn conversations.
|