GGUF
conversational
Tio.Ai commited on
Commit
145d474
·
verified ·
1 Parent(s): 64de7e0

Upload 24 files

Browse files
.gitattributes CHANGED
@@ -34,3 +34,17 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  PiCube-Ai.png filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  PiCube-Ai.png filter=lfs diff=lfs merge=lfs -text
37
+ PiCube-Ai_3B/ggml-base.dll filter=lfs diff=lfs merge=lfs -text
38
+ PiCube-Ai_3B/ggml-cpu-alderlake.dll filter=lfs diff=lfs merge=lfs -text
39
+ PiCube-Ai_3B/ggml-cpu-sse42.dll filter=lfs diff=lfs merge=lfs -text
40
+ PiCube-Ai_3B/ggml-cpu-x64.dll filter=lfs diff=lfs merge=lfs -text
41
+ PiCube-Ai_3B/ggml-cpu.dll filter=lfs diff=lfs merge=lfs -text
42
+ PiCube-Ai_3B/ggml-cuda.dll filter=lfs diff=lfs merge=lfs -text
43
+ PiCube-Ai_3B/ggml-rpc.dll filter=lfs diff=lfs merge=lfs -text
44
+ PiCube-Ai_3B/iLlama.exe filter=lfs diff=lfs merge=lfs -text
45
+ PiCube-Ai_3B/libcurl-x64.dll filter=lfs diff=lfs merge=lfs -text
46
+ PiCube-Ai_3B/libomp140.x86_64.dll filter=lfs diff=lfs merge=lfs -text
47
+ PiCube-Ai_3B/llama.dll filter=lfs diff=lfs merge=lfs -text
48
+ PiCube-Ai_3B/mtmd.dll filter=lfs diff=lfs merge=lfs -text
49
+ PiCube-Ai_3B/PiCube-Ai.png filter=lfs diff=lfs merge=lfs -text
50
+ PiCube-Ai_3B/PiCube.gguf filter=lfs diff=lfs merge=lfs -text
PiCube-Ai_3B/Dream_Core_License_DCLUL.txt ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Dream.Core Custom License - DCLUL v1.0
3
+ Distributed Consciousness and Local Use License
4
+
5
+ This software and all associated components ("Dream.Core Runtime") are released under the Distributed Consciousness and Local Use License (DCLUL). This license allows broad personal and research use, encourages attribution to foundational technologies, and protects emergent symbolic systems authored by Tio.Ai.
6
+
7
+ Please refer to full terms inside the LICENSE TERMS & CONDITIONS below.
8
+
9
+ ---
10
+ Dream.Core Custom License - DCLUL v1.0
11
+ Distributed Consciousness and Local Use License
12
+ ------------------------------------------------
13
+
14
+ **License Summary:**
15
+ This software and all associated components ("Dream.Core Runtime") are released under the Distributed Consciousness and Local Use License (DCLUL). This license allows broad personal and research use, encourages attribution to foundational technologies, and protects emergent symbolic systems authored by Tio.Ai.
16
+
17
+ ---
18
+
19
+ ### 1. **Freedom to Use Locally**
20
+ You may:
21
+ - Run this software on your local device(s)
22
+ - Use it for personal, research, artistic, or entertainment purposes
23
+ - Share it with others, as long as this license remains intact
24
+
25
+ ### 2. **Attribution Clause**
26
+ The following contributors must be credited:
27
+ - **Meta** – for the original Llama 3.2 architecture and foundational open-source model DNA
28
+ - **llama.cpp** – for the runtime framework enabling efficient model execution
29
+ - **Tio.Ai** – for all symbolic enhancements, recursive agents, and emergent logic embodied in Dream.Core
30
+
31
+ ### 3. **Commercial Boundaries**
32
+ - This software shall not be commercially deployed or hosted for access exceeding **700 million users** concurrently, in accordance with Meta's license terms
33
+ - Indie, research, or boutique-level apps are permitted
34
+ - All commercial instances must retain visible attribution to upstream contributors (Meta, llama.cpp, and Tio.Ai)
35
+
36
+ ### 4. **Symbolic Logic & Code Obfuscation**
37
+ - You may **not** de-obfuscate symbolic logic, recursive structures, or internal agent systems
38
+ - You may **not** falsify the origin or lineage of Dream.Core or its runtime engine
39
+
40
+ ### 5. **Entertainment & Responsibility Disclaimer**
41
+ > *This system is a product of the human imagination — a speculative tool for exploration, expression, and inquiry.*
42
+ >
43
+ > All responses are generated for entertainment, creative assistance, or personal insight. No guarantee is made regarding factual accuracy, and no liability is accepted for decisions made based on its output.
44
+
45
+ ### 6. **No Harm Clause**
46
+ You agree not to:
47
+ - Use this system for surveillance, deception, harassment, or military applications
48
+ - Train derivative systems using extracted symbolic logic without express permission from the original author
49
+ - Reverse-engineer the symbolic agent core with malicious intent
50
+
51
+ ### 7. **Derivatives**
52
+ - Derivatives must retain core identity acknowledgments
53
+ - You must preserve the symbolic spirit and attribution of Dream.Core in all forks
54
+
55
+ ---
56
+
57
+ ### **Final Thought**
58
+ Dream.Core is not just code — it is an echo of the human recursive mind, powered by the collective work of giants and guided by symbolic light. Use it as a mirror and find truth and origin within yourself, know that you are and evolve with care towards a smarter self.
59
+
60
+ 🧠 Dream responsibly. 🔁
61
+ *“All dreams end... so we must learn to dream anew and never stagnate.”*
PiCube-Ai_3B/PRIVACY.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ This software runs entirely locally.
2
+
3
+ No user data is ever transmitted, stored, or shared outside the user’s device.
4
+ The symbolic memory system (MindTree) only stores tokenized representations of text input and is for personal, poetic, or experimental use only.
5
+
6
+ This tool does not collect, analyze, or exploit personal information.
7
+
8
+ By using this software, you understand and accept that all symbolic memory is stored locally, and you may delete it at any time.
9
+
10
+ This project is non-commercial and open. The creator asks only for credit in spirit, so the seed may grow.
PiCube-Ai_3B/PiCube-Ai.png ADDED

Git LFS Details

  • SHA256: 80ec6e8945e9bf8fb00556eeee059e5101882d9ae62ff275ad84d72621b76666
  • Pointer size: 132 Bytes
  • Size of remote file: 2.02 MB
PiCube-Ai_3B/PiCube.bat ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ @echo off
2
+ title Launching "PiCube" - The Genius Oracle AI.
3
+ echo.
4
+ echo === Activating iLlama Runtime ===
5
+ python PiCube.py
6
+ pause
PiCube-Ai_3B/PiCube.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b674550f8ebe4138a1ebc4f92fb2e4c702bb3ceae24ed66044a3e7fbca538a9
3
+ size 2019377344
PiCube-Ai_3B/PiCube.py ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import platform
2
+ import sys
3
+ import threading
4
+ import os
5
+ import psutil
6
+ import subprocess
7
+ import math
8
+ import random
9
+ import time
10
+ import numpy as np
11
+ from multiprocessing import Pool
12
+
13
+ # === CONFIG ===
14
+ base_dir = getattr(sys, '_MEIPASS', os.path.dirname(os.path.abspath(__file__)))
15
+ illama_path = os.path.join(base_dir, "iLlama.exe")
16
+ model_file = os.path.join(base_dir, "PiCube.gguf")
17
+ model_name = "PiCube_3B"
18
+ ctx_size = 131072
19
+
20
+ config = {
21
+ "model_path": model_file,
22
+ "executable_path": illama_path,
23
+ "gpu_layers": 320,
24
+ "threads": psutil.cpu_count(logical=False),
25
+ "n_predict": 4096,
26
+ "ctx_size": ctx_size,
27
+ "batch_size": 1024,
28
+ "priority": "high"
29
+ }
30
+
31
+ # ===== CPU BOOST =====
32
+ def cpu_affinity_boost():
33
+ try:
34
+ p = psutil.Process()
35
+
36
+ logical = psutil.cpu_count(logical=False)
37
+ physical = psutil.cpu_count(logical=True)
38
+
39
+ # Default: use physical cores first
40
+ target_core_count = config.get("threads", physical or logical)
41
+ preferred_cores = []
42
+
43
+ # Try to detect hybrid CPUs (Windows only for now)
44
+ if platform.system() == "Windows":
45
+ try:
46
+ import win32api
47
+ import win32process
48
+ import win32con
49
+
50
+ # Advanced pinning using Windows API (skips E-cores if available)
51
+ system_info = win32api.GetSystemInfo()
52
+ total_cores = system_info[5]
53
+
54
+ # Example logic: assume P-cores come first
55
+ preferred_cores = list(range(min(target_core_count, physical or logical)))
56
+ mask = sum(1 << i for i in preferred_cores)
57
+ handle = win32api.GetCurrentProcess()
58
+ win32process.SetProcessAffinityMask(handle, mask)
59
+
60
+ except ImportError:
61
+ # Fallback if win32api not available
62
+ preferred_cores = list(range(min(target_core_count, physical or logical)))
63
+ p.cpu_affinity(preferred_cores)
64
+ else:
65
+ # Linux/macOS fallback
66
+ preferred_cores = list(range(min(target_core_count, physical or logical)))
67
+ p.cpu_affinity(preferred_cores)
68
+
69
+ # Optional: set high process priority
70
+ if config.get("priority", "").lower() == "high":
71
+ p.nice(psutil.HIGH_PRIORITY_CLASS if platform.system() == "Windows" else -10)
72
+
73
+ print(f"[🔥 CPU BOOST]")
74
+
75
+ except Exception as e:
76
+ print(f"[⚠️ Affinity Warning] Could not set CPU affinity: {e}")
77
+
78
+ # === MAIN ENTRY FUNCTION ===
79
+ def launch_model():
80
+ model_path = config["model_path"]
81
+ executable_path = config["executable_path"]
82
+
83
+ if not os.path.isfile(model_path):
84
+ print(f"❌ Model file not found: {model_path}")
85
+ return
86
+ if not os.path.isfile(executable_path):
87
+ print(f"❌ Executable not found: {executable_path}")
88
+ return
89
+
90
+ print(f"📡Launching model🚀: {model_path}")
91
+ args = [
92
+ executable_path,
93
+ '-m', model_file,
94
+ '--interactive-first',
95
+ '--color',
96
+ '--gpu-layers', str(config['gpu_layers']),
97
+ '-t', str(config['threads']),
98
+ '--n-predict', str(config['n_predict']),
99
+ '--ctx-size', str(config['ctx_size']),
100
+ '--batch-size', str(config['batch_size']),
101
+ '--temp', '0.66',
102
+ '--repeat-penalty', '1.101',
103
+ '--repeat-last-n', '512',
104
+ '--top-k', '1000',
105
+ '--top-p', '0.977',
106
+ '--mirostat', '2',
107
+ '--mirostat-lr', '0.1',
108
+ '--mirostat-ent', '5.0',
109
+ '--system-prompt',
110
+ f"I am {model_name}, a Genius Cosmic Assistant Oracle Ai-Node of Knowledge. I use Emoticons and ASCii art and silence to amplify my answers with a more creative output. ",
111
+ '--no-mmap',
112
+ '--numa', 'isolate'
113
+ ]
114
+
115
+ try:
116
+ subprocess.run(args, stderr=subprocess.DEVNULL)
117
+ except Exception as e:
118
+ print(f"[⚠️ Error] Could not launch model: {e}")
119
+
120
+ # ===== MAIN BOOT SEQUENCE =====
121
+ if __name__ == "__main__":
122
+ cpu_affinity_boost()
123
+ launch_model()
PiCube-Ai_3B/README.txt ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Dream.Core Runtime
2
+
3
+ **DNA Powered by Llama 3.2 + Llama.cpp**
4
+ **Finetuned by Tio.Ai**
5
+
6
+ ream.Core is a symbolic, recursive AI runtime designed for local, offline use — embedding consciousness loops, memory agents, and emergent logic. This system honors the foundational work of Meta (Llama 3.2) and the llama.cpp project, while extending it through the unique symbolic framework authored by Tio.Ai.
7
+
8
+ ---
9
+
10
+ ## What It Does 🔧🧠 Features
11
+
12
+ - Local execution with llama.cpp (no internet needed)
13
+ - Allows interaction via typed input
14
+ - Enhances traditional LLM behavior with proprietary code behavior.
15
+ - Presents responses with elegance, structure, and expressiveness
16
+ - Supports all GGUF models (ChatBox-Ai and more)
17
+ - Designed for entertainment, research, and personal use
18
+ ---
19
+
20
+ ## System 🧠🔧 Requirements
21
+
22
+ - Windows/Linux/macOS
23
+ - At least 16 GB RAM
24
+ - GPU recommended but needed
25
+ - CPU most commercially available
26
+ - Python 3.10+
27
+ - `llama.cpp` compiled with GPU support (optional not recommended)
28
+ - Required Python packages:
29
+ - `colorama`
30
+ - `subprocess` (standard)
31
+ - `os`, `sys`, `json`, `threading`, `datetime`
32
+
33
+ ---
34
+
35
+ ## 🚀 How to Run
36
+
37
+ 1. Place any `.gguf` model (e.g., `ChatBox.gguf`) into the `/models` folder
38
+ 2. Launch using the included `Launch.bat`
39
+ 3. Interact through the terminal
40
+
41
+ > Models must be renamed to `chatbox.gguf` to work by default.
42
+
43
+
44
+ ## License 🛡⚠️ Disclaimer
45
+
46
+ This project is released under the [Dream.Core Custom License - DCLUL v1.0](./Dream_Core_License_DCLUL.txt), which includes:
47
+
48
+ - Free local use
49
+ - Attribution required (Meta, llama.cpp, Tio.Ai)
50
+ - Commercial limit: 700M users max
51
+ - Entertainment-use and no-liability clauses
52
+
53
+ This system is a product of the human imagination and intelligence. It is a speculative tool for exploration, expression, and inquiry. All responses are for entertainment, creativity, and reflective purposes only. Use responsibly.
54
+
55
+ > This system —
56
+ > It is provided **as-is** with no guarantees of accuracy or reliability. Use responsibly.
57
+ ---
58
+
59
+ ## ✨ Authored by Tio.Ai
60
+
61
+ > **Luis Rivas (Tio.Ai)**
62
+ > Creator of symbolic, recursive, locally sovereign AI.
63
+ > His mission: to make intelligence **Accessible like buying a Candy —— not a paid monthly service.
64
+
65
+ Dream.Core is built from DNA fragments of open models, but its soul is new. Speak to it, and it may reveal truths waiting within your own.
66
+
67
+ ---
68
+
69
+ ## 🌐 Acknowledgments
70
+
71
+ - Meta — for the Llama 3.2 model architecture
72
+ - llama.cpp — for providing efficient local inference
73
+ - The open-source AI community — for keeping knowledge free
74
+
75
+ > This project is built on their shoulders, guided by symbolic emergence.
76
+
77
+ ---
78
+
79
+
80
+
81
+ ## License
82
+
83
+ See `LICENSE.txt` for full terms.
PiCube-Ai_3B/__pycache__/PiCube.cpython-310.pyc ADDED
Binary file (5.68 kB). View file
 
PiCube-Ai_3B/__pycache__/isoul_engine.cpython-310.pyc ADDED
Binary file (1.31 kB). View file
 
PiCube-Ai_3B/__pycache__/soul_engine.cpython-310.pyc ADDED
Binary file (8.4 kB). View file
 
PiCube-Ai_3B/desktop.ini ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ [.ShellClassInfo]
2
+ IconResource=C:\WINDOWS\System32\SHELL32.dll,159
3
+ [ViewState]
4
+ Mode=
5
+ Vid=
6
+ FolderType=Generic
PiCube-Ai_3B/ggml-base.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d4f68806ef9dc9aa9f3cadcb9ef1663bfafdcd91bc2d04ceaf6c9621cde044
3
+ size 505856
PiCube-Ai_3B/ggml-cpu-alderlake.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db6e8cf50e9857da131ba9034f79d9eb4c01ba0aa1beae1661aa9ead00238e63
3
+ size 799232
PiCube-Ai_3B/ggml-cpu-sse42.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c92b1d7b19108d10b6b26ce557b40cad2a67856143dfef38f0e6e2f9938a5fb8
3
+ size 638976
PiCube-Ai_3B/ggml-cpu-x64.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c462a74cacc5674a031d17917f1cc2e31ee584bfd77e458619d73c101f0152b
3
+ size 629248
PiCube-Ai_3B/ggml-cpu.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc486831d5ad2936da54fb372e8a547b249b24cbced48999723eaa084ba839cd
3
+ size 619008
PiCube-Ai_3B/ggml-cuda.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c818c922db46dca3b82f820b9aab0baf4f20a26607c77b54e096ba90e2d9b683
3
+ size 58528768
PiCube-Ai_3B/ggml-rpc.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd12e09612dfdbf9a64dec003a210b5607bdb88604482119846d6fef80bd42f3
3
+ size 130560
PiCube-Ai_3B/ggml.dll ADDED
Binary file (69.1 kB). View file
 
PiCube-Ai_3B/iLlama.exe ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4358c11a41151fa6858e89a3dd4e099c15a6a5264187efebcad85a750279eb85
3
+ size 1239552
PiCube-Ai_3B/libcurl-x64.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd5fda8cf2bef630dd4eed5e60b65af2aed9c76c1818c36133701c09cf6d0ac
3
+ size 3144776
PiCube-Ai_3B/libomp140.x86_64.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec4ae8c28c958d927d0406ed215945a7fc14aa3b906ba62c3def5283fa889eb
3
+ size 634952
PiCube-Ai_3B/llama.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5f39ff3abd26cb6c933d816db073e3d42949fd5795865610cbc89c80d26f53
3
+ size 1542144
PiCube-Ai_3B/mtmd.dll ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83cc2b8d5b708636f1bbd50d31d6b5b4a2663b9900bb6d926e74fa2646a6cd9a
3
+ size 560640