Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: openrail
|
| 3 |
+
datasets:
|
| 4 |
+
- JeanKaddour/minipile
|
| 5 |
+
- Open-Orca/OpenOrca
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
---
|
| 9 |
+
Micro Mistral
|
| 10 |
+
This is a small mistral model with 6 layers
|
| 11 |
+
|
| 12 |
+
It is similar to smol llama varaints uses GQA and tied embeddings. Except it uses mistral style arch with GQA and sliding window attention
|
| 13 |
+
|
| 14 |
+
This architecture takes GQA and tied embeddings to create an effeceint 0.5B model that uses the mistral architecture(It is supported in downstream applications)
|
| 15 |
+
|
| 16 |
+
Dataset
|
| 17 |
+
Minipile Instruct Math OpenOrca Synthetic Data
|
| 18 |
+
|
| 19 |
+
TODO: Complete Dataset section
|