Update README.md
Browse files
README.md
CHANGED
@@ -11,12 +11,17 @@ base_model:
|
|
11 |
|
12 |
license: apache-2.0
|
13 |
---
|
|
|
|
|
14 |
|
15 |
-
|
16 |
|
17 |
# NeuTrixOmniBe-DPO
|
18 |
|
19 |
NeuTrixOmniBe-DPO is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
|
|
|
|
|
|
20 |
```yaml
|
21 |
MODEL_NAME = "NeuTrixOmniBe-DPO"
|
22 |
yaml_config = """
|
@@ -36,12 +41,13 @@ parameters:
|
|
36 |
value: [1, 0.5, 0.7, 0.3, 0]
|
37 |
- value: 0.5
|
38 |
dtype: bfloat16
|
39 |
-
"""
|
|
|
40 |
|
41 |
It was then trained with DPO using:
|
42 |
* Intel/orca_dpo_pairs
|
43 |
|
44 |
-
|
45 |
|
46 |
|
47 |
|
|
|
11 |
|
12 |
license: apache-2.0
|
13 |
---
|
14 |
+
# This model was merged, trained, and so on, thanks to the knowledge I gained from reading Maxime Labonne's course. Special thanks to him!
|
15 |
+
[Labonne LLM Course](https://github.com/mlabonne/llm-course)
|
16 |
|
17 |
+
![NeuTrixOmniBe](https://raw.githubusercontent.com/kukedlc87/imagenes/main/DALL%C2%B7E%202023-12-29%2002.13.09%20-%20A%20robot%20with%20a%20unique%20design%20where%20its%20face%20is%20a%20screen%20displaying%20binary%20code.%20The%20robot's%20body%20is%20sleek%20and%20modern%2C%20with%20a%20metallic%20finish%20that%20refl.png)
|
18 |
|
19 |
# NeuTrixOmniBe-DPO
|
20 |
|
21 |
NeuTrixOmniBe-DPO is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
22 |
+
|
23 |
+
## 🧩 Configuration
|
24 |
+
|
25 |
```yaml
|
26 |
MODEL_NAME = "NeuTrixOmniBe-DPO"
|
27 |
yaml_config = """
|
|
|
41 |
value: [1, 0.5, 0.7, 0.3, 0]
|
42 |
- value: 0.5
|
43 |
dtype: bfloat16
|
44 |
+
"""
|
45 |
+
```
|
46 |
|
47 |
It was then trained with DPO using:
|
48 |
* Intel/orca_dpo_pairs
|
49 |
|
50 |
+
|
51 |
|
52 |
|
53 |
|