Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,25 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nd-4.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
### (Uses ~9GB of Vram at 4Bit, obviously the model performs better at higher precision)
|
| 5 |
|
| 6 |
# Colab NoteBook:
|
| 7 |
https://colab.research.google.com/drive/1gkmMOVQ_P-NGIRuK3Kj3gWJat33MHNi8#scrollTo=LGQ8BiMuXMDG
|
| 8 |
|
| 9 |
# YouTube:
|
| 10 |
-
https://www.youtube.com/watch?v=IiVlO4JBZaU
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nd-4.0
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
A small local model, with 15 Billion Parameters and 32k Context Length.
|
| 6 |
+
|
| 7 |
+
This is one of my experiemental models I created playing with pruning, ablation, and training curriculums rather than many epochs of the same data set.
|
| 8 |
+
|
| 9 |
+
```
|
| 10 |
+
This model was trained on a
|
| 11 |
+
- Python Code Instruct Dataset,
|
| 12 |
+
- My Hand curated knowledge graphs manually formatted in Mermaid Chart to be able to export as images using MMDC.
|
| 13 |
+
- Context Obedient for the RAG usecase to process many chunks of information and make sense of it without making things up.
|
| 14 |
+
```
|
| 15 |
+
|
| 16 |
+
Now trained on my personal companion dataset has led to a model that listens to instructions really well and stays context relevant, while also aware of its situation in the universe and its role to the user.
|
| 17 |
+
|
| 18 |
### (Uses ~9GB of Vram at 4Bit, obviously the model performs better at higher precision)
|
| 19 |
|
| 20 |
# Colab NoteBook:
|
| 21 |
https://colab.research.google.com/drive/1gkmMOVQ_P-NGIRuK3Kj3gWJat33MHNi8#scrollTo=LGQ8BiMuXMDG
|
| 22 |
|
| 23 |
# YouTube:
|
| 24 |
+
https://www.youtube.com/watch?v=IiVlO4JBZaU
|
| 25 |
+
|