Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- cerebras/Qwen3-Coder-REAP-25B-A3B
|
| 5 |
+
tags:
|
| 6 |
+
- code
|
| 7 |
+
- pruned
|
| 8 |
+
---
|
| 9 |
+
This is a layer-wise pruned variant of cerebras/Qwen3-Coder-REAP-25B-A3B resulting in a ~20B model with ~3B active parameters.
|
| 10 |
+
|
| 11 |
+
Prune info:
|
| 12 |
+
Original model: 48 layers
|
| 13 |
+
**New model: 38 Layers**
|
| 14 |
+
|
| 15 |
+
result:
|
| 16 |
+
Similar model, it MUST be fine-tuned before usage as current performance is non-ideal. While it can absolutely be used as is, fine-tuning is needed.
|