Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,7 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
## Qwen3 Highlights
|
| 4 |
|
|
@@ -12,9 +15,9 @@ Building upon extensive advancements in training data, model architecture, and o
|
|
| 12 |
|
| 13 |
## Model Overview
|
| 14 |
|
| 15 |
-
**Qwen3-4B** has the following features:
|
| 16 |
- Type: Causal Language Models
|
| 17 |
-
- Training Stage: Pretraining
|
| 18 |
- Number of Parameters: 4.0B
|
| 19 |
- Number of Paramaters (Non-Embedding): 3.6B
|
| 20 |
- Number of Layers: 36
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
# Qwen3-4B-Base
|
| 5 |
|
| 6 |
## Qwen3 Highlights
|
| 7 |
|
|
|
|
| 15 |
|
| 16 |
## Model Overview
|
| 17 |
|
| 18 |
+
**Qwen3-4B-Base** has the following features:
|
| 19 |
- Type: Causal Language Models
|
| 20 |
+
- Training Stage: Pretraining
|
| 21 |
- Number of Parameters: 4.0B
|
| 22 |
- Number of Paramaters (Non-Embedding): 3.6B
|
| 23 |
- Number of Layers: 36
|