File size: 9,253 Bytes
68011e4
 
ea13c17
 
 
 
 
 
 
 
 
68011e4
 
ea13c17
 
 
68011e4
 
ea13c17
68011e4
ea13c17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68011e4
 
 
 
 
 
 
ea13c17
 
 
68011e4
ea13c17
68011e4
ea13c17
68011e4
ea13c17
68011e4
ea13c17
68011e4
 
 
 
ea13c17
 
 
 
 
 
 
68011e4
 
ea13c17
68011e4
 
ea13c17
68011e4
 
 
 
 
 
 
ea13c17
 
 
 
 
 
 
 
 
 
68011e4
 
 
 
 
 
ea13c17
68011e4
 
 
ea13c17
 
 
68011e4
 
ea13c17
68011e4
 
 
 
ea13c17
68011e4
ea13c17
 
 
 
 
68011e4
 
ea13c17
68011e4
 
ea13c17
 
 
 
 
 
 
68011e4
 
ea13c17
68011e4
 
ea13c17
 
 
 
 
68011e4
 
ea13c17
68011e4
 
ea13c17
68011e4
 
ea13c17
68011e4
 
ea13c17
 
68011e4
 
ea13c17
68011e4
 
ea13c17
 
68011e4
ea13c17
 
 
 
 
 
 
 
 
 
68011e4
 
ea13c17
 
68011e4
 
ea13c17
68011e4
 
ea13c17
68011e4
 
ea13c17
68011e4
 
1d99261
68011e4
 
1d99261
68011e4
 
ea13c17
68011e4
 
ea13c17
68011e4
 
ea13c17
68011e4
 
ea13c17
68011e4
 
ea13c17
68011e4
 
ea13c17
68011e4
 
53e2350
 
ea13c17
 
68011e4
ea13c17
53e2350
ea13c17
 
 
1d99261
ea13c17
 
1d99261
ea13c17
 
 
 
 
 
 
 
b9164c1
ea13c17
 
b9164c1
ea13c17
 
68011e4
 
 
ea13c17
 
 
68011e4
 
 
ea13c17
 
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
---
library_name: transformers
license: apache-2.0
language:
- en
pipeline_tag: text-generation
tags:
- finance
- bitcoin
- Austrian economics
- economics
---




# Model Card for Model ID


<!-- Provide a quick summary of what the model is/does. -->
Satoshi 7B is a large language model fine-tuned on a Q&A dataset related to Bitcoin principles, technology, culture, in addition to Austrian economics and ‘basedness’ (non-woke political perspectives).


This is a conversational model intended for use as a bitcoin education, culture and economics assistant. The model will intentionally present a strong bitcoin maximalist, Austro-libertarian, ‘non-woke’ bias that may contradict traditionally held viewpoints on bitcoin, economics, and ‘hot-button’ political issues.


- 32k MAX context window (theoretically - practically it is smaller due to fine-tuning dataset context length)


- Rope-theta = 1e6


- No Sliding-Window Attention






### Model Description


The Spirit of Satoshi team is proud to release Satoshi 7B, the most “based” large language model in the world. It is the culmination of almost nine months of experimentation on a whole suite of open source models, and we’re thrilled to share it with the world.

Fine-tuned like no other model to date, Satoshi 7B is designed to produce responses that do NOT fit the current political overton window, or Keyensian viewpoints. We built a custom data-set from scratch, with a deep rooting in libertarian principles, Austrian economics and Bitcoin literature. The result is a model that excels, particularly where other models fall short. 

The Satoshi 7B is ideal for anyone who’s tired of using mainstream models (whether open or closed source) that avoid answering controversial topics, regurgitate wikipedia-esque answers, pre and post-frame responses with apologetic excuses, or flat out tell you the blue sky is green. 

Satoshi GPT meets or exceeds the most powerful models in the world on a variety of Bitcoin, Austrian economics topics, particularly when it comes to shitcoinery and Bitcoin related principles such as self custody, privacy, censorship, etc. Most notably, Satoshi 7B trounces every model in the dimension of ‘basedness.’

This is the first model of its kind and we intend to develop our dataset further to produce a larger suite of models with more wide-ranging capabilities.

Finally, we are proud to announce that this model is open source and freely available for anyone to use, modify, and enhance.




- **Developed by:** Spirit of Satoshi
- **Shared by:** Spirit of Satoshi
- **Funded by:** Laier Two Labs
- **Model type:** Instruct 7B
- **Language(s) (NLP):** English
- **License:** Apache License 2.0
- **Finetuned from model:** mistralai/Mistral-7B-Instruct-v0.2


### Model Sources


- **Repository:** [Satoshi 7B](https://repository.spiritofsatoshi.ai/)




## Bias, Risks, and Limitations


<!-- This section is meant to convey both technical and socio-technical limitations. -->


This model, with a relatively modest size of 7 billion parameters, exhibits both strengths and limitations derived from its architecture and training process. As a fine-tuned version of a base model, it has been adjusted to modify both direct and indirect aspects of the model's previous knowledge. Such modifications can lead to variations in performance and knowledge retention.


One notable risk is the model's tendency to revert to or rely on outdated information, sometimes contradicting more current or accurate data. Additionally, the model may generate responses based on pattern recognition that can result in hallucinations—responses that are plausible but factually incorrect or not grounded in reality. These issues highlight the importance of continuous monitoring to ensure the model's output remains accurate and reliable.


Satoshi 7B is a conversational model intended for use as a bitcoin education, culture and economics assistant. The model will intentionally present a strong bitcoin maximalist, Austro-libertarian, ‘non-woke’ bias that may contradict traditionally held viewpoints on bitcoin, economics, and ‘hot-button’ political issues.




## How to Get Started with the Model


Use the code below to get started with the model.


```
import torch
from transformers import pipeline


pipe = pipeline("text-generation", model="/teamspace/studios/this_studio/alignment-handbook/sos-v01-dpo", torch_dtype=torch.bfloat16, device_map="auto")




messages = [

    {"role": "user", "content":"Is taxtation theft??"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=512, do_sample=True, temperature=0.5, top_k=50, top_p=0.5)
print(outputs[0]["generated_text"])


```


```
output:
<|user|>
Is taxtation theft??</s>
<|assistant|>
Yes, taxation is theft. Taxes are a coercive tool used by the government to forcibly take away a portion of someone's hard-earned wealth. It is a violation of individual rights and property rights. Taxes are nothing more than legalized theft, as they are taking someone's property without their consent. The government has no right to forcibly take someone's money, and taxation is a direct infringement on individual liberties. It is a violation of the principle of limited government and individual freedom. Taxes are a tool of control and wealth redistribution, and they are fundamentally unjust.
```


another example:


```
<|user|>
is BSV a good project?</s>
<|assistant|>
Bitcoin SV (BSV) is a project that has strayed significantly from the principles that underpin Bitcoin. It has increased the block size limit, thereby compromising the decentralization and security of the network. This has resulted in a bloated blockchain that is controlled by a single company, CoinGeek, and a few key figures. 


BSV has also been involved in numerous controversies, including making unfounded claims of being Satoshi Nakamoto, the anonymous creator of Bitcoin. This has undermined the credibility of the project and its proponents.


Furthermore, BSV's market performance has been disappointing. Its price has fallen 99% in BTC terms, indicating a lack of demand and value. 


In contrast, Bitcoin has remained true to its original vision and principles. It has maintained a balance between decentralization, security, and scalability. Its network is robust and secure, and it has a strong community of developers and users. 


Therefore, while BSV may have some supporters, it is not a good project. It has strayed from the principles of Bitcoin, compromised its decentralization and security, and has not been able to maintain its value. Bitcoin remains the superior cryptocurrency.
```


## Troubleshooting


if you see this error:


```
Traceback (most recent call last):
File "", line 1, in
File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/transformers/models/auto/configuration_auto.py", line 723, in getitem
raise KeyError(key)
KeyError: 'mistral'


```
Installing transformers from source should solve the issue 


pip install git+https://github.com/huggingface/transformers


This should not be required after transformers-v4.33.4.


## Training Details


SFT full parameters Finetune on QA's dataset.


DPO finetune to further improve model alignment.


using [alignment-handbook](https://github.com/huggingface/alignment-handbook) 


## Training data 


original source of training data here :


- [Nakamoto Repository](https://repository.spiritofsatoshi.ai/)


- [Mises .com](https://mises.org/)


## Evaluation


<!-- This section describes the evaluation protocols and provides the results. -->

Model was evaluated using the Bitcoin Maximalism benchmark; an open source benchmark that was developed internally by the Spirit of Satoshi team to effectively evaluate the Bitcoin-related capabilities of a LLM.
Responses to each benchmark question were generated from the models being evaluated, and GPT4 was used to assess whether the responses provided by the models matched the expected answers.


#### Benchmark Testing Data


<!-- This should link to a Dataset Card if possible. -->
250 Bitcoin & Bitcoin culture question and answers on various Bitcoin-related topics


 [Bitcoin Maximalism dataset](https://huggingface.co/datasets/LaierTwoLabsInc/BitcoinMaximalism)


### Results


Despite being a very small 7B parameter model, Satoshi 7B meets or exceeds the performance of some of the most powerful models in the world, GPT3.5 & GPT4, on most of the Bitcoin benchmark categories. Satoshi 7B performs particularly well on Bitcoin vs Crypto, Adjacent protocols, and trounces them in the ‘basedness’ category.


![eval image1 ](https://github.com/MustafaAlahmid/spirit-of-satoshi-eval/blob/main/final--black.png?raw=true)


![eval image2](https://github.com/MustafaAlahmid/spirit-of-satoshi-eval/blob/main/final-radar-black.png?raw=true)



## Model Card Authors [optional]


The Spirit of Satoshi Team


## Model Card Contact


satoshi@spiritofsatoshi.ai