SicariusSicariiStuff commited on
Commit
5942d94
β€’
1 Parent(s): 8180eec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +119 -3
README.md CHANGED
@@ -1,3 +1,119 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ ---
6
+
7
+ <div align="center">
8
+ <b style="font-size: 40px;">Zion_Alpha_Instruction_Tuned_GGUF</b>
9
+
10
+
11
+ </div>
12
+
13
+
14
+ <img src="https://i.imgur.com/e1LEQ18.png" alt="Zion_Alpha_Instruction_Tuned" style="width: 50%; min-width: 400px; display: block; margin: auto;">
15
+
16
+
17
+ # Model Details
18
+
19
+ Zion_Alpha is the first **REAL** Hebrew model in the world. This version WAS fine tuned for tasks. I did the finetune using SOTA techniques and using my insights from years of underwater basket weaving. If you wanna offer me a job, just add me on Facebook.
20
+
21
+ # Future Plans
22
+ I plan to perform a SLERP merge with one of my other fine-tuned models, which has a bit more knowledge about Israeli topics. Additionally, I might create a larger model using MergeKit, but we'll see how it goes.
23
+
24
+ # Looking for Sponsors
25
+ Since all my work is done on-premises, I am constrained by my current hardware. I would greatly appreciate any support in acquiring an A6000, which would enable me to train significantly larger models much faster.
26
+
27
+ # Contact Details
28
+ I'm not great at self-marketing (tp say the least) and don't have any social media accounts. If you'd like to reach out to me, you can email me at [email protected]. Please note that this email might receive more messages than I can handle, so I apologize in advance if I can't respond to everyone.
29
+
30
+ # Versions and QUANTS
31
+ - Base model: [FP16](https://huggingface.co/SicariusSicariiStuff/Zion_Alpha)
32
+ - Instruction tuned: [FP16](https://huggingface.co/SicariusSicariiStuff/Zion_Alpha_Instruction_Tuned) | [GGUF](https://huggingface.co/SicariusSicariiStuff/Zion_Alpha_Instruction_Tuned_GGUF)
33
+
34
+
35
+ # Model architecture
36
+ Based on Mistral 7B. I didn't even bother to alter the tokenizer.
37
+
38
+ # The recommended prompt setting is Debug-deterministic:
39
+ ```
40
+ temperature: 1
41
+ top_p: 1
42
+ top_k: 1
43
+ typical_p: 1
44
+ min_p: 1
45
+ repetition_penalty: 1
46
+ ```
47
+
48
+ # The recommended instruction template is Mistral:
49
+ ```
50
+ {%- for message in messages %}
51
+ {%- if message['role'] == 'system' -%}
52
+ {{- message['content'] -}}
53
+ {%- else -%}
54
+ {%- if message['role'] == 'user' -%}
55
+ {{-'[INST] ' + message['content'].rstrip() + ' [/INST]'-}}
56
+ {%- else -%}
57
+ {{-'' + message['content'] + '</s>' -}}
58
+ {%- endif -%}
59
+ {%- endif -%}
60
+ {%- endfor -%}
61
+ {%- if add_generation_prompt -%}
62
+ {{-''-}}
63
+ {%- endif -%}
64
+ ```
65
+ # English to hebrew example:
66
+
67
+
68
+ <div align="center">
69
+ <b style="font-size: 40px;">Zion_Alpha English to Hebrew example</b>
70
+
71
+
72
+ </div>
73
+
74
+
75
+ <img src="https://i.imgur.com/JnTuawF.png" alt="Zion_Alpha" style="width: 40%; min-width: 600px; display: block; margin: auto;">
76
+
77
+
78
+ # English to hebrew example:
79
+
80
+
81
+ <div align="center">
82
+ <b style="font-size: 40px;">Zion_Alpha Hebrew to English example</b>
83
+
84
+
85
+ </div>
86
+
87
+
88
+ <img src="https://i.imgur.com/Wm2igLJ.png" alt="Zion_Alpha" style="width: 40%; min-width: 600px; display: block; margin: auto;">
89
+
90
+
91
+ <div align="center">
92
+ <b style="font-size: 30px;">Unscripted video: live zero shot demonstration at story writing capabilities in Hebrew</b>
93
+
94
+ [![Zion_Alpha Story writing](https://img.youtube.com/vi/YYKeovnS0do/0.jpg)](https://www.youtube.com/watch?v=YYKeovnS0do)
95
+ </div>
96
+
97
+ <div align="center">
98
+ <b style="font-size: 30px;">Zion_Alpha VS Mistral 'Hebrew' Live & unscripted in real time</b>
99
+
100
+ [![Zion_Alpha Story writing](https://img.youtube.com/vi/YYKeovnS0do/0.jpg)](https://www.youtube.com/watch?v=DQFtx8M2txc)
101
+ </div>
102
+
103
+ <div align="center">
104
+ <b style="font-size: 30px;">Zion_Alpha VS Mistral 'Hebrew' Live & unscripted in real time Long text translation</b>
105
+
106
+ [![Zion_Alpha Story writing](https://img.youtube.com/vi/YYKeovnS0do/0.jpg)](https://www.youtube.com/watch?v=w5fz3Ot6tH8)
107
+ </div>
108
+
109
+ ### History
110
+ The model was originally trained about 2 month after Mistral (v0.1) was released.
111
+ As of 04 June 2024, Zion_Alpha got the **Highest SNLI score in the world** among open source models in Hebrew, surpassing most of the models by a huge margin. (**84.05** score)
112
+ <img src="https://i.imgur.com/7HokS5w.png" alt="Zion_Alpha SNLI Score" style="width: 80%; min-width: 700px; display: block; margin: auto;">
113
+
114
+ ### Support
115
+ <img src="https://i.imgur.com/0lHHN95.png" alt="GPUs too expensive" style="width: 10%; min-width: 100px; display: block; margin: left;">
116
+
117
+ - [My Ko-fi page](https://ko-fi.com/sicarius) ALL donations will go for research resources and compute, every bit counts πŸ™πŸ»
118
+ - [My Patreon](https://patreon.com/TenebraAI) ALL donations will go for research resources and compute, every bit counts πŸ™πŸ»
119
+