File size: 8,423 Bytes
dabc2e4
c57427d
dabc2e4
 
 
 
 
 
 
d25a807
dabc2e4
 
 
c57427d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dabc2e4
 
d966fab
dabc2e4
efe7a3a
a9bf71d
9a3effd
45a9624
c717ff8
dabc2e4
 
 
 
 
c236a87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b2e2f7f
c236a87
d8eddb1
c236a87
dabc2e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45a9624
fc501a8
bdb710a
dabc2e4
 
 
 
 
 
 
 
 
 
 
 
9f367ff
 
d01b3fa
9f367ff
 
c57427d
 
 
 
 
 
 
 
 
 
 
 
 
 
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
---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- Kukedlc/NeuralKrishna-7B-v3
- Kukedlc/NeuralMarioMonarch-7B-slerp
- liminerity/M7-7b
base_model:   
- Kukedlc/NeuralKrishna-7B-v3
- Kukedlc/NeuralMarioMonarch-7B-slerp
- liminerity/M7-7b
model-index:
- name: NeuralSirKrishna-7b
  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: 73.72
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
      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: 89.05
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
      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: 64.63
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
      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: 75.6
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
      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: 85.32
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
      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: 71.27
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
      name: Open LLM Leaderboard
---

<div align="center" style="font-size: 44px;">🧞 NeuralSirKrishna-7b</div>

## πŸ‘©β€πŸ’» Try here! 
    
[Talking to Sir Neural Krishna 7b](https://huggingface.co/spaces/Kukedlc/Neural-Sir-Krishna-7b-GGUF)
![NeuralSirKrishna-7b](https://raw.githubusercontent.com/kukedlc87/imagenes/main/DALL%C2%B7E%202024-02-17%2005.09.10%20-%20Imagine%20a%20large%20language%20model%20represented%20as%20an%20abstract%2C%20ethereal%20entity%2C%20made%20of%20swirling%20codes%20and%20data%20streams%2C%20lying%20on%20a%20classic%20psychoanalysis.webp)

NeuralKrishna-7B-v4 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Kukedlc/NeuralKrishna-7B-v3](https://huggingface.co/Kukedlc/NeuralKrishna-7B-v3)
* [Kukedlc/NeuralMarioMonarch-7B-slerp](https://huggingface.co/Kukedlc/NeuralMarioMonarch-7B-slerp)
* [liminerity/M7-7b](https://huggingface.co/liminerity/M7-7b)

# Chat 

- User: Create an advanced theory about the origin of life on earth that is new, innovative, and disruptive, totally new with no resemblance to anything else but at the same time that can be real.

- System: I. The Symbiotic Cosmic Initiation Hypothesis (SCIH)

To propose a groundbreaking and disruptive theory about the origin of life on Earth, let's envision an interconnected web of cosmic events that transcends conventional understanding. The Symbiotic Cosmic Initiation Hypothesis (SCIH) posits that life didn't arise from a singular event or molecular accident but rather from a complex, multifaceted interplay between extraterrestrial entities and our planet's nascent environment. Here are its core tenets:

1. Prebiotic Symbionts: SCIH rejects the notion of a solitary "building block" or "spark of life." Instead, it postulates that prebiotic symbionts – self-replicating, organic-inorganic complexes – arrived on Earth from space via meteorites and comets. These symbionts, composed of a diverse array of biomolecules and mineral catalysts, were the products of extraterrestrial ecosystems or "astrobiomes."

2. Astrobiome Cross-Fertilization: The constant exchange of matter between our solar system's planets and asteroid belts facilitated the transfer of these prebiotic symbionts across vast distances. This cosmic symbiosis allowed for the intermingling of genetic and catalytic material, fostering evolutionary innovation and adaptability among these extraterrestrial life-forms.

3. Terrestrial Integration and Adaptation: Upon impacting Earth's surface, these prebiotic symbionts began to integrate with our planet's pre-existing chemical milieu. The resulting synergy between Earth-born and extraterrestrial biomolecules accelerated the formation of more complex organic structures, eventually leading to protocells – rudimentary, self-enclosed systems capable of rudimentary metabolism and replication.

4. The Catalytic Gaian Boost: As Earth's early atmosphere evolved to become more hospitable to life, a positive feedback loop between these protocells and our planet's environment ensued. The emergence of photosynthesis and other metabolic processes contributed to the creation of a self-regulating, life-nurturing environment – what we now call the Ga
  

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/-Dzd1TwuUVX-wNdScI2Hb.png)

## 🧩 Configuration

```yaml
models:
  - model: Kukedlc/NeuralKrishna-7B-v3
    # no parameters necessary for base model
  - model: Kukedlc/NeuralKrishna-7B-v3
    parameters:
      density: 0.65
      weight: 0.36
  - model: Kukedlc/NeuralMarioMonarch-7B-slerp
    parameters:
      density: 0.6
      weight: 0.34
  - model: liminerity/M7-7b
    parameters:
      density: 0.4
      weight: 0.3
merge_method: dare_ties
base_model: Kukedlc/NeuralKrishna-7B-v3
parameters:
  int8_mask: true
dtype: bfloat16
random_seed: 0
```

## πŸ’» Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/NeuralSirKrishna-7b"
messages = [{"role": "user", "content": """Create an advanced theory about the origin of life on earth that is new,
innovative, and disruptive, totally new with no resemblance to anything else but at the same time that can be real."""}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

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"])
```

# πŸƒ Family models:

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/y4_aqj7zR1yXnuKi5oiMH.png)

# [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_Kukedlc__NeuralSirKrishna-7b)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |76.60|
|AI2 Reasoning Challenge (25-Shot)|73.72|
|HellaSwag (10-Shot)              |89.05|
|MMLU (5-Shot)                    |64.63|
|TruthfulQA (0-shot)              |75.60|
|Winogrande (5-shot)              |85.32|
|GSM8k (5-shot)                   |71.27|