Update README.md
Browse files
README.md
CHANGED
@@ -1,39 +1,25 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
-
-
|
4 |
-
-
|
5 |
library_name: transformers
|
|
|
6 |
tags:
|
7 |
-
-
|
8 |
-
-
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
## Merge Details
|
16 |
-
### Merge Method
|
17 |
-
|
18 |
-
This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
|
19 |
-
|
20 |
-
### Models Merged
|
21 |
-
|
22 |
-
The following models were included in the merge:
|
23 |
-
* [deca-ai/2-mini-beta-2-11](https://huggingface.co/deca-ai/2-mini-beta-2-11)
|
24 |
-
* [Blazgo/2-mini-beta-002](https://huggingface.co/Blazgo/2-mini-beta-002)
|
25 |
-
|
26 |
-
### Configuration
|
27 |
|
28 |
-
|
29 |
|
30 |
-
|
31 |
-
|
32 |
-
- model: Blazgo/2-mini-beta-002
|
33 |
-
- model: deca-ai/2-mini-beta-2-11
|
34 |
-
merge_method: slerp
|
35 |
-
base_model: deca-ai/2-mini-beta-2-11
|
36 |
-
dtype: bfloat16
|
37 |
-
parameters:
|
38 |
-
t: [1, 0, 1, 0.5, 0]
|
39 |
-
```
|
|
|
1 |
---
|
2 |
base_model:
|
3 |
+
- Qwen/Qwen2.5-14B-Instruct-1M
|
4 |
+
- deepseek-ai/DeepSeek-R1
|
5 |
library_name: transformers
|
6 |
+
license: cc-by-nc-nd-4.0
|
7 |
tags:
|
8 |
+
- reasoning
|
9 |
+
- R1
|
10 |
+
- 1M
|
11 |
+
- fast
|
12 |
+
- Deca
|
13 |
+
- Deca-AI
|
14 |
+
- Deca-2
|
15 |
+
- Qwen
|
16 |
---
|
17 |
+
## This is the old version of Deca 2 mini. Use deca-ai/2-mini-beta
|
18 |
+
The Deca 2 family of models is currently in BETA
|
19 |
+

|
20 |
+
The Deca 2 family of models, currently in BETA, is built on cutting-edge architectures like DeepSeek R1, and Qwen 2, delivering extraordinary performance. With a focus on insane speed and high efficiency, Deca 2 is revolutionizing text generation and setting new standards in the industry. It also comes with a **1 million** context window.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
|
22 |
+
As more capabilities are added, Deca 2 will evolve into a more powerful, any-to-any model in the future. While it’s focused on text generation for now, its foundation is designed to scale, bringing even more advanced functionalities to come.
|
23 |
|
24 |
+
* **2/14 Realase:**
|
25 |
+
* Enhanced Instruction Following
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|