Update README.md
Browse files
README.md
CHANGED
@@ -1,40 +1,19 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
-
-
|
4 |
-
- NobodyExistsOnTheInternet/code-llama-70b-python-instruct
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
-
- mergekit
|
8 |
- merge
|
9 |
-
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
-
# merge
|
12 |
-
|
13 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
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 |
-
* [Blazgo/2-pro-base](https://huggingface.co/Blazgo/2-pro-base)
|
24 |
-
* [NobodyExistsOnTheInternet/code-llama-70b-python-instruct](https://huggingface.co/NobodyExistsOnTheInternet/code-llama-70b-python-instruct)
|
25 |
-
|
26 |
-
### Configuration
|
27 |
|
28 |
-
|
|
|
29 |
|
30 |
-
|
31 |
-
models:
|
32 |
-
- model: Blazgo/2-pro-base
|
33 |
-
- model: NobodyExistsOnTheInternet/code-llama-70b-python-instruct
|
34 |
-
merge_method: slerp
|
35 |
-
base_model: Blazgo/2-pro-base
|
36 |
-
dtype: bfloat16
|
37 |
-
parameters:
|
38 |
-
t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
|
39 |
|
40 |
-
|
|
|
1 |
---
|
2 |
base_model:
|
3 |
+
- deca-ai/2-pro-base
|
|
|
4 |
library_name: transformers
|
5 |
tags:
|
|
|
6 |
- merge
|
7 |
+
- reasoning
|
8 |
+
- R1
|
9 |
+
- Deca
|
10 |
+
- Deca-AI
|
11 |
+
- uncensored
|
12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
+

|
15 |
+
The Deca 2 `PRO` model, currently in BETA, is built on cutting-edge architectures like Perplexity's R1 1776, LLaMA 3, and Qwen 2, delivering extraordinary performance. With a focus on insane speed and high efficiency, Deca 2 `PRO` is revolutionizing text generation and setting new standards in the industry.
|
16 |
|
17 |
+
As more capabilities are added, Deca 2 `PRO` 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.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
+
This model is trained on code-related tasks.
|