Hugging Face's logo

RichardErkhov
/
Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
RichardErkhov commited on
Commit
d0b4f02
·
verified ·
1 Parent(s): a0acc38

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +102 -0
README.md ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ NIHAPPY-L3.1-8B-v0.09 - GGUF
11
+ - Model creator: https://huggingface.co/Arkana08/
12
+ - Original model: https://huggingface.co/Arkana08/NIHAPPY-L3.1-8B-v0.09/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [NIHAPPY-L3.1-8B-v0.09.Q2_K.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q2_K.gguf) | Q2_K | 2.96GB |
18
+ | [NIHAPPY-L3.1-8B-v0.09.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
19
+ | [NIHAPPY-L3.1-8B-v0.09.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.IQ3_S.gguf) | IQ3_S | 3.43GB |
20
+ | [NIHAPPY-L3.1-8B-v0.09.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
21
+ | [NIHAPPY-L3.1-8B-v0.09.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.IQ3_M.gguf) | IQ3_M | 3.52GB |
22
+ | [NIHAPPY-L3.1-8B-v0.09.Q3_K.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q3_K.gguf) | Q3_K | 3.74GB |
23
+ | [NIHAPPY-L3.1-8B-v0.09.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
24
+ | [NIHAPPY-L3.1-8B-v0.09.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
25
+ | [NIHAPPY-L3.1-8B-v0.09.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
26
+ | [NIHAPPY-L3.1-8B-v0.09.Q4_0.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q4_0.gguf) | Q4_0 | 4.34GB |
27
+ | [NIHAPPY-L3.1-8B-v0.09.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
28
+ | [NIHAPPY-L3.1-8B-v0.09.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
29
+ | [NIHAPPY-L3.1-8B-v0.09.Q4_K.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q4_K.gguf) | Q4_K | 4.58GB |
30
+ | [NIHAPPY-L3.1-8B-v0.09.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
31
+ | [NIHAPPY-L3.1-8B-v0.09.Q4_1.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q4_1.gguf) | Q4_1 | 4.78GB |
32
+ | [NIHAPPY-L3.1-8B-v0.09.Q5_0.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q5_0.gguf) | Q5_0 | 5.21GB |
33
+ | [NIHAPPY-L3.1-8B-v0.09.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
34
+ | [NIHAPPY-L3.1-8B-v0.09.Q5_K.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q5_K.gguf) | Q5_K | 5.34GB |
35
+ | [NIHAPPY-L3.1-8B-v0.09.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
36
+ | [NIHAPPY-L3.1-8B-v0.09.Q5_1.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q5_1.gguf) | Q5_1 | 5.65GB |
37
+ | [NIHAPPY-L3.1-8B-v0.09.Q6_K.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q6_K.gguf) | Q6_K | 6.14GB |
38
+ | [NIHAPPY-L3.1-8B-v0.09.Q8_0.gguf](https://huggingface.co/RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf/blob/main/NIHAPPY-L3.1-8B-v0.09.Q8_0.gguf) | Q8_0 | 7.95GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ base_model: []
46
+ library_name: transformers
47
+ tags:
48
+ - mergekit
49
+ - merge
50
+
51
+ ---
52
+ ### (GGUF) Thanks mradermacher
53
+
54
+ - **GGUF:** **[mradermacher/NIHAPPY-L3.1-8B-v0.09-GGUF](https://huggingface.co/mradermacher/NIHAPPY-L3.1-8B-v0.09-GGUF)**
55
+ - **imatrix GGUF:** **[mradermacher/NIHAPPY-L3.1-8B-v0.09-i1-GGUF](https://huggingface.co/mradermacher/NIHAPPY-L3.1-8B-v0.09-i1-GGUF)**
56
+
57
+ **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.
58
+
59
+ ## Merge Details
60
+
61
+ ### Merge Method
62
+ 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.
63
+
64
+ ### Models Merged
65
+ The following models were included in the merge:
66
+
67
+ - **[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.
68
+ - **[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.
69
+ - **[v000000/L3-8B-Poppy-Moonfall-C](https://huggingface.co/v000000/L3-8B-Poppy-Moonfall-C)**: Focuses on storytelling, imagination, and creative expression.
70
+
71
+ ## Configuration
72
+
73
+ The following YAML configuration was used to produce NIHAPPY:
74
+
75
+ ```yaml
76
+ models:
77
+ - model: v000000/L3.1-Niitorm-8B-DPO-t0.0001
78
+ parameters:
79
+ weight: 0.35
80
+ density: 0.65
81
+ - model: v000000/L3-8B-Poppy-Moonfall-C
82
+ parameters:
83
+ weight: 0.45
84
+ density: 0.65
85
+ - model: Nitral-AI/Hathor_Tahsin-L3-8B-v0.85
86
+ parameters:
87
+ weight: 0.20
88
+ density: 0.68
89
+ merge_method: dare_ties
90
+ base_model: v000000/L3.1-Niitorm-8B-DPO-t0.0001
91
+ parameters:
92
+ int8_mask: true
93
+ dtype: bfloat16
94
+ ```
95
+
96
+ ## Credits
97
+ Thanks to the creators of the models:
98
+
99
+ - **[Nitral-AI/Hathor_Tahsin-L3-8B-v0.85](https://huggingface.co/Nitral-AI/Hathor_Tahsin-L3-8B-v0.85)**
100
+ - **[v000000/L3.1-Niitorm-8B-DPO-t0.0001](https://huggingface.co/v000000/L3.1-Niitorm-8B-DPO-t0.0001)**
101
+ - **[v000000/L3-8B-Poppy-Moonfall-C](https://huggingface.co/v000000/L3-8B-Poppy-Moonfall-C)**
102
+