thwinthithtoo15 commited on
Commit
16bb41e
Β·
verified Β·
1 Parent(s): 22dbd08

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +68 -40
README.md CHANGED
@@ -1,69 +1,97 @@
1
- license: openrail language:
2
 
3
- en tags:
4
 
5
- rust
6
 
7
- edge-ai
8
-
9
- custom-model
10
-
11
- tokenizer
12
-
13
- self-attention
14
-
15
- πŸš€ OpenCreate Ai v1 - Edge AI Model
16
-
17
- OpenCreate Ai v1 is a lightweight, local Edge AI model implementation written entirely in Rust. It features a custom-built architecture including a Tokenizer, Embedding Matrix, Self-Attention mechanism, and Next-Token Prediction pipeline designed for efficient text and code generation on edge devices.
18
-
19
- πŸ› οΈ Model Architecture
20
 
21
  The model consists of four core modular layers implemented from scratch in Rust:
22
 
23
- Custom Tokenizer:
 
 
24
 
25
- Builds a vocabulary directly from the training corpus.
 
26
 
27
- Handles text encoding (string to token IDs) and decoding (token IDs back to text).
 
28
 
29
- Embedding Layer:
 
30
 
31
- Transforms token IDs into dense mathematical vectors (vocab_size x embedding_dim) using custom weights.
 
32
 
33
- Self-Attention Mechanism:
34
 
35
- Captures contextual relationships and dependencies between tokens for basic reasoning and comprehension.
36
 
37
- Prediction Layer (Linear / Next-Token):
38
 
39
- Computes context vectors to predict and generate the next sequential token for text writing or code completion.
 
 
 
40
 
41
- Document & Search Pipeline:
 
 
 
42
 
43
- Local search indexing and text output processing pipeline.
44
 
45
- πŸ’» Getting Started (Local Run)
46
 
47
- Ensure you have Rust & Cargo installed on your system.
48
 
49
- Clone the repository / Open project folder:
 
 
 
50
 
51
- cd OpenCreateAI
 
 
52
 
53
- Run the model via Cargo:
 
54
 
55
- cargo run
 
56
 
57
- πŸ“Š Sample Output
 
 
 
58
 
59
- When executed locally, the model processes prompts and generates tokens as follows:
 
 
60
 
61
- ================================================== # OpenCreate Ai v1 - Edge AI Model Initialized [1] Tokenization Process: Input Prompt : OpenCreate Encoded IDs : [0, 1, 2, 3, 4, 5, 2, 6, 7, 2]
62
 
63
- [2] Embedding Matrix Generated successfully. [3] Self-Attention Mechanism Applied (Reasoning active).
 
 
 
 
64
 
65
- [4] Generation & Output Result: Generated Output Text/Code : OpenCreatea
66
 
67
- [5] Document & Search Pipeline: # Status: Local Search Indexing & Document Export Ready. πŸ“„ License
68
 
69
- This project is licensed under the OpenRAIL (Open Responsible AI License). By using, downloading, or modifying this model, you agree to comply with the terms and conditions promoting safe, responsible, and ethical AI deployment.
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # πŸš€ OpenCreate Ai v1 - Edge AI Model
2
 
3
+ **OpenCreate Ai v1** is a lightweight, local Edge AI model implementation written entirely in Rust. It features a custom-built architecture including a Tokenizer, Embedding Matrix, Self-Attention mechanism, and Next-Token Prediction pipeline designed for efficient text and code generation on edge devices.
4
 
5
+ ---
6
 
7
+ ## πŸ› οΈ Model Architecture
 
 
 
 
 
 
 
 
 
 
 
 
8
 
9
  The model consists of four core modular layers implemented from scratch in Rust:
10
 
11
+ ### 1. Custom Tokenizer
12
+ - Builds a vocabulary directly from the training corpus.
13
+ - Handles text encoding (string to token IDs) and decoding (token IDs back to text).
14
 
15
+ ### 2. Embedding Layer
16
+ - Transforms token IDs into dense mathematical vectors (`vocab_size Γ— embedding_dim`) using custom weights.
17
 
18
+ ### 3. Self-Attention Mechanism
19
+ - Captures contextual relationships and dependencies between tokens for basic reasoning and comprehension.
20
 
21
+ ### 4. Prediction Layer (Linear / Next-Token)
22
+ - Computes context vectors to predict and generate the next sequential token for text writing or code completion.
23
 
24
+ ### 5. Document & Search Pipeline
25
+ - Local search indexing and text output processing pipeline.
26
 
27
+ ---
28
 
29
+ ## πŸ’» Getting Started (Local Run)
30
 
31
+ Ensure you have Rust & Cargo installed on your system.
32
 
33
+ ### 1. Clone the repository / Open project folder
34
+ ```bash
35
+ cd OpenCreateAI
36
+ ```
37
 
38
+ ### 2. Run the model via Cargo
39
+ ```bash
40
+ cargo run
41
+ ```
42
 
43
+ ---
44
 
45
+ ## πŸ“Š Sample Output
46
 
47
+ When executed locally, the model processes prompts and generates tokens as follows:
48
 
49
+ ```text
50
+ ==================================================
51
+ OpenCreate Ai v1 - Edge AI Model Initialized
52
+ ==================================================
53
 
54
+ [1] Tokenization Process:
55
+ Input Prompt : OpenCreate
56
+ Encoded IDs : [0, 1, 2, 3, 4, 5, 2, 6, 7, 2]
57
 
58
+ [2] Embedding Matrix Generated successfully.
59
+ [3] Self-Attention Mechanism Applied (Reasoning active).
60
 
61
+ [4] Generation & Output Result:
62
+ Generated Output Text/Code : OpenCreatea
63
 
64
+ [5] Document & Search Pipeline:
65
+ Status: Local Search Indexing & Document Export Ready.
66
+ ==================================================
67
+ ```
68
 
69
+ ---
70
+
71
+ ## πŸ“„ License
72
 
73
+ This project is licensed under the **OpenRAIL** (Open Responsible AI License). By using, downloading, or modifying this model, you agree to comply with the terms and conditions promoting safe, responsible, and ethical AI deployment.
74
 
75
+ | Meta Info | Value |
76
+ |-----------|-------|
77
+ | **License** | openrail |
78
+ | **Language** | en |
79
+ | **Tags** | `rust`, `edge-ai`, `custom-model`, `tokenizer`, `self-attention` |
80
 
81
+ ---
82
 
83
+ ## Project Structure
84
 
85
+ ```
86
+ OpenCreateAI/
87
+ β”œβ”€β”€ Cargo.toml
88
+ β”œβ”€β”€ src/
89
+ β”‚ β”œβ”€β”€ main.rs
90
+ β”‚ β”œβ”€β”€ tokenizer.rs
91
+ β”‚ β”œβ”€β”€ embedding.rs
92
+ β”‚ β”œβ”€β”€ attention.rs
93
+ β”‚ β”œβ”€β”€ prediction.rs
94
+ β”‚ └── search.rs
95
+ └── data/
96
+ └── corpus.txt
97
+ ```