Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,7 @@ In comparison with the previous released Mobius, the improvements include:
|
|
13 |
* Significant performance improvement;
|
14 |
* Multilingual support ;
|
15 |
* Stable support of 128K context length.
|
|
|
16 |
|
17 |
|
18 |
## Usage
|
@@ -21,7 +22,7 @@ We encourage you use few shots to use this model, Desipte Directly use User: xxx
|
|
21 |
## More details
|
22 |
Mobius 12B 128k based on RWKV v5.2 arch, which is leading state based RNN+CNN+Transformer Mixed language large language model which focus opensouce community
|
23 |
* 10~100 trainning/inference cost reduce;
|
24 |
-
* state based,which mean good at
|
25 |
* community support.
|
26 |
|
27 |
## requirements
|
@@ -33,4 +34,4 @@ Mobius 12B 128k based on RWKV v5.2 arch, which is leading state based RNN+CNN+Tr
|
|
33 |
## future plan
|
34 |
If you need a HF version let us know
|
35 |
|
36 |
-
[Mobius-Chat-12B-128k](https://huggingface.co/TimeMobius/Mobius-Chat-12B-128k)
|
|
|
13 |
* Significant performance improvement;
|
14 |
* Multilingual support ;
|
15 |
* Stable support of 128K context length.
|
16 |
+
* Base model [Mobius-mega-12B-128k-base](https://huggingface.co/TimeMobius/Moibus-mega-12B-128k-base)
|
17 |
|
18 |
|
19 |
## Usage
|
|
|
22 |
## More details
|
23 |
Mobius 12B 128k based on RWKV v5.2 arch, which is leading state based RNN+CNN+Transformer Mixed language large language model which focus opensouce community
|
24 |
* 10~100 trainning/inference cost reduce;
|
25 |
+
* state based,selected memory, which mean good at grok;
|
26 |
* community support.
|
27 |
|
28 |
## requirements
|
|
|
34 |
## future plan
|
35 |
If you need a HF version let us know
|
36 |
|
37 |
+
[Mobius-Chat-12B-128k](https://huggingface.co/TimeMobius/Mobius-Chat-12B-128k)
|