File size: 6,425 Bytes
0c39869
 
 
 
 
 
10dd21c
 
2cb6483
0c39869
 
6a1e1b8
 
0c39869
eb0a2aa
 
43cd93a
e25e2f4
0c39869
cdd37e1
6a1e1b8
 
 
cdd37e1
6a1e1b8
0d5f1d8
6a1e1b8
 
 
9f84c97
c856a1b
 
 
 
b3479d6
 
6a1e1b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9feaa9c
 
 
 
 
 
 
6a1e1b8
 
 
3d2bfcd
 
 
 
 
 
 
 
 
 
 
 
 
6a1e1b8
 
3d2bfcd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6a1e1b8
 
 
0c39869
 
 
 
 
 
 
6a1e1b8
 
0c39869
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
---
license: apache-2.0
tags:
- moe
- merge
- mergekit
- Solar Moe
- Solar
- Umbra
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/TN6IeT8hHjMCVljzVn2Fs.png)

# Umbra-MoE-4x10.7

GGUF Files Kindly provided By [@Kquant03](https://huggingface.co/Kquant03)

[GGUF FILES HERE](https://huggingface.co/Kquant03/Umbra-MoE-4x10.7-GGUF)

Umbra is an off shoot of the [Lumosia Series] with a Focus in General Knowledge and RP/ERP

This model was built around the idea someone wanted a General Assiatant that could also tell Stories/RP/ERP when wanted.

This is a very experimental model. It's a combination MoE of Solar models, the models selected are personal favorites.

base context is 4k but it stays coherent up to 16k

Please let me know how the model works for you.


Update:

A Umbra Personality tavern card has been added to the files.

Template:

```
### System:

### USER:{prompt}

### Assistant:
```


Settings:
```
Temp: 1.0
min-p: 0.02-0.1
```

## Evals:

* Avg: 73.4
* ARC: 70.31
* HellaSwag: 87.81
* MMLU: 66.42
* T-QA: 67.82
* Winogrande: 83.27
* GSM8K: 64.75

## Examples:
```

User:
Tell me an interesting fact.

Umbra:
The Amazon Rainforest is home to an astounding variety of life forms.

It encompasses over five million square kilometers across nine South American countries and holds approximately one-third of all known species on Earth.

This biodiversity hotspot supports more than 390 billion individual trees representing 16,000 species.

Over two million insect species live here alongside thousands of bird, mammal, amphibian, and reptile species. In this dense forest, indigenous communities have developed intricate knowledge systems that allow them to thrive sustainably within their surroundings.

```
```

User:
Tell me a story about a red haired fox

Umbra:
In the enchanted forest of Ardenwood, a vibrant world teeming with life and magic, lived a curious creature known as Vixie, whose russet fur glowed against the verdure that surrounded her. Her emerald eyes twinkled with mischief and wonder as she roamed the lush landscape, befriending all who crossed her path.

One sunlit afternoon, Vixie found herself weaving amongst a sea of tall grasses swaying gently in the breeze. Ahead lay a shimmering riverbank, where a gathering of animals was assembled around a mystifying sight - a radiant stone pulsing with an ethereal glow.

A majestic stag approached Vixie, his voice resonating with authority. He introduced himself as Elthon, leader of this assembly. They had gathered to seek guidance from the celestial gem, said to hold the secrets of the universe within its sparkling depths.

Vixie, filled with curiosity, asked if she could partake in their quest for knowledge. Elthon agreed, and they each took turns gazing into the jewel. As Vixie's turn came, she felt a tingling sensation course through her body, her senses heightened as the stone revealed a vision before her.

In the dreamlike tableau, Vixie saw herself standing atop a hill overlooking Ardenwood. She watched as the seasons changed, the land thrived, and creatures played out their destinies. It appeared the fates of these beings were intertwined, a tapestry woven together by love, friendship, sacrifice, and growth.

When the trance subsided, Vixie returned to the present moment, feeling humbled and grateful. This revelation emboldened her desire to cherish those bonds she shared with others, knowing how vital they were to the beauty and harmony of the enchanted realm. From then on, Vixie continued her adventures with renewed purpose, nurturing friendships and embracing the mysteries of Ardenwood.

```

Umbra-MoE-4x10.7 is a Mixure of Experts (MoE) made with the following models using:
* [kodonho/SolarM-SakuraSolar-SLERP](https://huggingface.co/kodonho/SolarM-SakuraSolar-SLERP)
* [Sao10K/Sensualize-Solar-10.7B](https://huggingface.co/Sao10K/Sensualize-Solar-10.7B)
* [NousResearch/Nous-Hermes-2-SOLAR-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B)
* [fblgit/UNA-SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/fblgit/UNA-SOLAR-10.7B-Instruct-v1.0)

## 🧩 Configuration

```
base_model: kodonho/SolarM-SakuraSolar-SLERP
gate_mode: hidden
dtype: bfloat16
experts:
  - source_model: kodonho/SolarM-SakuraSolar-SLERP
    positive_prompts:
    - "versatile"
    - "helpful"
    - "factual"
    - "integrated"
    - "adaptive"
    - "comprehensive"
    - "balanced"
    negative_prompts:
    - "specialized"
    - "narrow"
    - "focused"
    - "limited"
    - "specific"

  - source_model: Sao10K/Sensualize-Solar-10.7B
    positive_prompts:
    - "creative"
    - "chat"
    - "discuss"
    - "culture"
    - "world"
    - "expressive"
    - "detailed"
    - "imaginative"
    - "engaging"
    negative_prompts:
    - "sorry"
    - "cannot"
    - "factual"
    - "concise"
    - "straightforward"
    - "objective"
    - "dry"

  - source_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
    positive_prompts:
    - "analytical"
    - "accurate"
    - "logical"
    - "knowledgeable"
    - "precise"
    - "calculate"
    - "compute"
    - "solve"
    - "work"
    - "python"
    - "javascript"
    - "programming"
    - "algorithm"
    - "tell me"
    - "assistant"
    negative_prompts:
    - "creative"
    - "abstract"
    - "imaginative"
    - "artistic"
    - "emotional"
    - "mistake"
    - "inaccurate"

  - source_model: fblgit/UNA-SOLAR-10.7B-Instruct-v1.0
    positive_prompts:
    - "instructive"
    - "clear"
    - "directive"
    - "helpful"
    - "informative"
    negative_prompts:
    - "exploratory"
    - "open-ended"
    - "narrative"
    - "speculative"
    - "artistic"
```

## 💻 Usage

```python
!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Steelskull/Umbra-MoE-4x10.7"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```