Arkana08 commited on
Commit
c25cc96
·
verified ·
1 Parent(s): 07ce851

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +57 -52
README.md CHANGED
@@ -1,53 +1,58 @@
1
- ---
2
- base_model: []
3
- library_name: transformers
4
- tags:
5
- - mergekit
6
- - merge
7
-
8
- ---
9
- **NIHAPPY** a role-playing model that seamlessly integrates the finest qualities of various pre-trained language models. Crafted with a focus on dynamic storytelling, NIHAPPY thrives in creative and immersive roleplaying environments. It masterfully balances intricate reasoning with a smooth and consistent narrative flow, ensuring an engaging and coherent experience.
10
-
11
- ## Merge Details
12
-
13
- ### Merge Method
14
- This model was created using the **DARE TIES** merge method, with **[v000000/L3.1-Niitorm-8B-DPO-t0.0001](https://huggingface.co/v000000/L3.1-Niitorm-8B-DPO-t0.0001)** serving as the base model. This approach ensures a fine-tuned balance between creativity, reasoning, and rule-following, ideal for intricate role-playing situations.
15
-
16
- ### Models Merged
17
- The following models were included in the merge:
18
-
19
- - **[Nitral-AI/Hathor_Tahsin-L3-8B-v0.85](https://huggingface.co/Nitral-AI/Hathor_Tahsin-L3-8B-v0.85)**: Contributes to rule-following, consistency, and character accuracy.
20
- - **[v000000/L3.1-Niitorm-8B-DPO-t0.0001](https://huggingface.co/v000000/L3.1-Niitorm-8B-DPO-t0.0001)**: A strong foundation for reasoning and logical responses.
21
- - **[v000000/L3-8B-Poppy-Moonfall-C](https://huggingface.co/v000000/L3-8B-Poppy-Moonfall-C)**: Focuses on storytelling, imagination, and creative expression.
22
-
23
- ## Configuration
24
-
25
- The following YAML configuration was used to produce NIHAPPY:
26
-
27
- ```yaml
28
- models:
29
- - model: v000000/L3.1-Niitorm-8B-DPO-t0.0001
30
- parameters:
31
- weight: 0.35
32
- density: 0.65
33
- - model: v000000/L3-8B-Poppy-Moonfall-C
34
- parameters:
35
- weight: 0.45
36
- density: 0.65
37
- - model: Nitral-AI/Hathor_Tahsin-L3-8B-v0.85
38
- parameters:
39
- weight: 0.20
40
- density: 0.68
41
- merge_method: dare_ties
42
- base_model: v000000/L3.1-Niitorm-8B-DPO-t0.0001
43
- parameters:
44
- int8_mask: true
45
- dtype: bfloat16
46
- ```
47
-
48
- ## Credits
49
- Thanks to the creators of the models:
50
-
51
- - **[Nitral-AI/Hathor_Tahsin-L3-8B-v0.85](https://huggingface.co/Nitral-AI/Hathor_Tahsin-L3-8B-v0.85)**
52
- - **[v000000/L3.1-Niitorm-8B-DPO-t0.0001](https://huggingface.co/v000000/L3.1-Niitorm-8B-DPO-t0.0001)**
 
 
 
 
 
53
  - **[v000000/L3-8B-Poppy-Moonfall-C](https://huggingface.co/v000000/L3-8B-Poppy-Moonfall-C)**
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ ### (GGUF) Thanks mradermacher
10
+
11
+ **GGUF:** **[mradermacher/NIHAPPY-L3.1-8B-v0.09-GGUF](https://huggingface.co/mradermacher/NIHAPPY-L3.1-8B-v0.09-GGUF)**
12
+ **imatrix GGUF:** **[mradermacher/NIHAPPY-L3.1-8B-v0.09-i1-GGUF](https://huggingface.co/mradermacher/NIHAPPY-L3.1-8B-v0.09-i1-GGUF)**
13
+
14
+ **NIHAPPY** a role-playing model that seamlessly integrates the finest qualities of various pre-trained language models. Crafted with a focus on dynamic storytelling, NIHAPPY thrives in creative and immersive roleplaying environments. It masterfully balances intricate reasoning with a smooth and consistent narrative flow, ensuring an engaging and coherent experience.
15
+
16
+ ## Merge Details
17
+
18
+ ### Merge Method
19
+ This model was created using the **DARE TIES** merge method, with **[v000000/L3.1-Niitorm-8B-DPO-t0.0001](https://huggingface.co/v000000/L3.1-Niitorm-8B-DPO-t0.0001)** serving as the base model. This approach ensures a fine-tuned balance between creativity, reasoning, and rule-following, ideal for intricate role-playing situations.
20
+
21
+ ### Models Merged
22
+ The following models were included in the merge:
23
+
24
+ - **[Nitral-AI/Hathor_Tahsin-L3-8B-v0.85](https://huggingface.co/Nitral-AI/Hathor_Tahsin-L3-8B-v0.85)**: Contributes to rule-following, consistency, and character accuracy.
25
+ - **[v000000/L3.1-Niitorm-8B-DPO-t0.0001](https://huggingface.co/v000000/L3.1-Niitorm-8B-DPO-t0.0001)**: A strong foundation for reasoning and logical responses.
26
+ - **[v000000/L3-8B-Poppy-Moonfall-C](https://huggingface.co/v000000/L3-8B-Poppy-Moonfall-C)**: Focuses on storytelling, imagination, and creative expression.
27
+
28
+ ## Configuration
29
+
30
+ The following YAML configuration was used to produce NIHAPPY:
31
+
32
+ ```yaml
33
+ models:
34
+ - model: v000000/L3.1-Niitorm-8B-DPO-t0.0001
35
+ parameters:
36
+ weight: 0.35
37
+ density: 0.65
38
+ - model: v000000/L3-8B-Poppy-Moonfall-C
39
+ parameters:
40
+ weight: 0.45
41
+ density: 0.65
42
+ - model: Nitral-AI/Hathor_Tahsin-L3-8B-v0.85
43
+ parameters:
44
+ weight: 0.20
45
+ density: 0.68
46
+ merge_method: dare_ties
47
+ base_model: v000000/L3.1-Niitorm-8B-DPO-t0.0001
48
+ parameters:
49
+ int8_mask: true
50
+ dtype: bfloat16
51
+ ```
52
+
53
+ ## Credits
54
+ Thanks to the creators of the models:
55
+
56
+ - **[Nitral-AI/Hathor_Tahsin-L3-8B-v0.85](https://huggingface.co/Nitral-AI/Hathor_Tahsin-L3-8B-v0.85)**
57
+ - **[v000000/L3.1-Niitorm-8B-DPO-t0.0001](https://huggingface.co/v000000/L3.1-Niitorm-8B-DPO-t0.0001)**
58
  - **[v000000/L3-8B-Poppy-Moonfall-C](https://huggingface.co/v000000/L3-8B-Poppy-Moonfall-C)**