Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
## Finetuned Model For My Thesis: Design And Implementation Of An Adaptive Virtual Intelligent Teaching Assistant Based On Supervised Fine-tuning Of A Pre-trained Large Language Model
|
| 5 |
+
### CodeOptimus：Supervised Instruction Fine-tuning [Mistral 7B Instruct](https://mistral.ai/news/announcing-mistral-7b/) using qLora.
|
| 6 |
+
|
| 7 |
+
## Prerequisites For Reproduction
|
| 8 |
+
1. **GPU**: Requires powerful GPUs, such as the A100.
|
| 9 |
+
2. **Python Packages**: Install requirements.txt.
|
| 10 |
+
3. **Dataset**: Download [code_instructions_122k_alpaca_style](https://huggingface.co/datasets/TokenBender/code_instructions_122k_alpaca_style) plus some custom curated dataset
|
| 11 |
+
4. **Mistra-7B-Instruct-v0.1**: Download [mistralai/Mistral-7B-Instruct-v0.1 ](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) pytorch bin weights
|
| 12 |
+
|
| 13 |
+
## Samples showing Adaptive Learning Capabilities
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|