|
@@ -166,9 +166,9 @@ Scaling neural networks to hundreds of billions of parameters has enabled dramat
|
|
|
### Blink/RWKV
|
|
|
| Size | Parameters | Link |
|
|
|
| ----- | ---------- | --------------------------------------------------- |
|
|
|
- | 169 M | 169 M | [Huggingface](https://huggingface.co/BlinkDL/rwkv-4-pile-169b) |
|
|
|
- | 430 M | 430 M | [Huggingface](https://huggingface.co/BlinkDL/rwkv-4-pile-430b) |
|
|
|
- | 1.5 B | 1.5 B | [Huggingface](https://huggingface.co/BlinkDL/rwkv-4-pile-1.5b) |
|
|
|
+ | 169 M | 169 M | [Huggingface](https://huggingface.co/BlinkDL/rwkv-4-pile-169m) |
|
|
|
+ | 430 M | 430 M | [Huggingface](https://huggingface.co/BlinkDL/rwkv-4-pile-430m) |
|
|
|
+ | 1.5 B | 1.5 B | [Huggingface](https://huggingface.co/BlinkDL/rwkv-4-pile-1b5) |
|
|
|
| 3 B | 3 B | [Huggingface](https://huggingface.co/BlinkDL/rwkv-4-pile-3b) |
|
|
|
| 7 B | 7 B | [Huggingface](https://huggingface.co/BlinkDL/rwkv-4-pile-7b) |
|
|
|
|