File size: 7,556 Bytes
07e18df
0c4080e
 
 
 
 
992548a
 
 
183a44c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
07e18df
 
f2a6785
 
0c4080e
07e18df
8668eaa
8de079d
93eb9da
3fa4871
8de079d
 
93eb9da
0561aa7
93eb9da
d9be7c3
 
 
 
 
884d363
0561aa7
 
93eb9da
0561aa7
 
 
a737a29
09f2a02
52e95f2
09f2a02
 
 
93eb9da
 
 
7f9484a
93eb9da
7f9484a
93eb9da
4fb85ac
884d363
 
 
 
 
 
 
4fb85ac
0c4080e
 
 
 
07e18df
93eb9da
 
2cbada7
 
 
 
 
 
 
93eb9da
884d363
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93eb9da
0c4080e
0f09075
8de079d
 
07e18df
 
 
 
 
 
 
 
 
 
8de079d
 
0c4080e
 
 
8de079d
 
0c4080e
 
 
 
 
 
 
 
 
 
 
 
 
 
07e18df
0c4080e
 
 
 
183a44c
 
 
 
 
 
 
 
 
 
 
 
 
 
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
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
---
license: apache-2.0
tags:
- moe
- merge
- mergekit
- Solar Moe
- Solar
- Lumosia
model-index:
- name: Lumosia-MoE-4x10.7
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 68.34
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Lumosia-MoE-4x10.7
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 87.13
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Lumosia-MoE-4x10.7
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 64.38
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Lumosia-MoE-4x10.7
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 63.81
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Lumosia-MoE-4x10.7
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 82.95
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Lumosia-MoE-4x10.7
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 51.02
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Lumosia-MoE-4x10.7
      name: Open LLM Leaderboard
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/Qb88YeudOf7MYuGKTirXC.png)

# Lumosia-MoE-4x10.7

"Lumosia" was selected as its a MoE of Multiple SOLAR Merges so it really "Lights the way".... its 3am.

This is a very experimantal model. its a MoE of all good performing Solar models (based off of personal experiance not open leaderboard), 
The models goal was to make a good all rounder, in chat/logic/rp

Why? Dunno whated to see what would happen

context is 4k but coherent up to 16k

Quants by @thebloke  (thank you)

https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF

https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ

Update: (Done)
Lumosia v1.5 has been uploaded.

Update 2:

A Lumosia Personality tavern card has been added

Come join the Discord:
[ConvexAI](https://discord.gg/yYqmNmg7Wj)


Template:
```
### System:

### USER:{prompt}

### Assistant:
```


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

Lumosia-MoE-4x10.7 is a Mixure of Experts (MoE) made with the following models:
* [DopeorNope/SOLARC-M-10.7B](https://huggingface.co/DopeorNope/SOLARC-M-10.7B)
* [maywell/PiVoT-10.7B-Mistral-v0.2-RP](https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2-RP)
* [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
* [jeonsworld/CarbonVillain-en-10.7B-v1](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v1)

## Evals:

* Avg: 69.61
* ARC: 68.34
* HellaSwag: 87.13
* MMLU: 64.38
* T-QA: 63.81
* Winogrande: 82.95
* GSM8K: 51.02

## Examples:
```
Example 1:

User:
Hello lumi, what is the meaning of life
in around 100 words.

Lumosia:
The meaning of life can vary greatly
depending on individual beliefs,
values, and experiences. One common
perspective suggests that the primary
purpose of life is to seek happiness,
fulfillment, and personal growth
through relationships
accomplishments, and spiritual
awareness. Living with integrity.
compassion, and gratitude while
making a positive impact on others
and the world around us can also
contribute to finding meaning in life
UItimately, the meaning of life is
subjective and unique to each
individual, who must define it for
themselves through exploration
reflection, and personal choice.

```
```
Example 2:

User:
Explain a MoE (Mixture of Experts) in
around 100 words

Lumosia:
A MoE, short for Mixture of Experts, is
a machine learning technique utilized
in ensemble learning. It involves
combining multiple specialist models
(experts) to optimize predictive
performance. Each expert focuses on
a subset of the input features or data
domains, making them specialized in
particular areas. Through a weighting
mechanism, like Gaussian Mixture
Model, the predictions of experts are
blended to produce a final result. MoE
models demonstrate effectiveness in
handling complex or ambiguous
inputs where a single model might
struggle. They are commonly used in
natural language processing.
computer vision, and speech synthesis.
```

## 🧩 Configuration

```
yamlbase_model: DopeorNope/SOLARC-M-10.7B
gate_mode: hidden
dtype: bfloat16
experts:
  - source_model: DopeorNope/SOLARC-M-10.7B
    positive_prompts: [""]
  - source_model: maywell/PiVoT-10.7B-Mistral-v0.2-RP
    positive_prompts: [""]
  - source_model: kyujinpy/Sakura-SOLAR-Instruct
    positive_prompts: [""]
  - source_model: jeonsworld/CarbonVillain-en-10.7B-v1
    positive_prompts: [""]
```

## 💻 Usage

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

from transformers import AutoTokenizer
import transformers
import torch

model = "Steelskull/Lumosia-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"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Steelskull__Lumosia-MoE-4x10.7)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |69.61|
|AI2 Reasoning Challenge (25-Shot)|68.34|
|HellaSwag (10-Shot)              |87.13|
|MMLU (5-Shot)                    |64.38|
|TruthfulQA (0-shot)              |63.81|
|Winogrande (5-shot)              |82.95|
|GSM8k (5-shot)                   |51.02|