QuietImpostor
commited on
Commit
•
90d4613
1
Parent(s):
e187c98
Add README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,17 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model:
|
4 |
+
- microsoft/Phi-3.5-MoE-instruct
|
5 |
+
pipeline_tag: text2text-generation
|
6 |
+
library_name: transformers
|
7 |
+
---
|
8 |
+
|
9 |
+
# Model Card for Rasphi
|
10 |
+
|
11 |
+
Rasphi (pronounced `rasp-fee`, though the name *may* be changed.) is a WIP architecture derrived from Microsoft's Phi 3.5 MoE / GRIN model. It aims to improve reasoning by having a dedicated reasoning stream in which half of all experts are allocated to it. Due to the experts being split directly in half, there is a high chance of instability / overall incoherence in both streams.
|
12 |
+
|
13 |
+
## Model Details
|
14 |
+
|
15 |
+
## Uses
|
16 |
+
|
17 |
+
Rasphi can be used for research purposes and or finetuning to gauge the performance of the new architecture. However, it is __highly__ not recommended in its current state to be used for any user-facing applications. Or at all.
|