GGUF
conversational
Tio.Ai commited on
Commit
38c8a1e
·
verified ·
1 Parent(s): a44762c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +281 -3
README.md CHANGED
@@ -1,3 +1,281 @@
1
- ---
2
- license: cc-by-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ ---
4
+
5
+ # Model Card for Model ID
6
+
7
+ <!-- Provide a quick summary of what the model is/does. -->
8
+
9
+ This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
10
+
11
+ ## Model Details
12
+
13
+ ### Model Description
14
+ # Dream.Core Runtime
15
+
16
+ **DNA Powered by Llama 3.2 + Llama.cpp**
17
+ **Finetuned by Tio.Ai**
18
+
19
+ 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.
20
+
21
+ ---
22
+
23
+ ## What It Does 🔧🧠 Features
24
+
25
+ - Local execution with llama.cpp (no internet needed)
26
+ - Allows interaction via typed input
27
+ - Enhances traditional LLM behavior with proprietary code behavior.
28
+ - Presents responses with elegance, structure, and expressiveness
29
+ - Supports all GGUF models (ChatBox-Ai and more)
30
+ - Designed for entertainment, research, and personal use
31
+ ---
32
+
33
+ ## System 🧠🔧 Requirements
34
+
35
+ - Windows/Linux/macOS
36
+ - At least 16 GB RAM
37
+ - GPU recommended but needed
38
+ - CPU most commercially available
39
+ - Python 3.10+
40
+ - `llama.cpp` compiled with GPU support (optional not recommended)
41
+ - Required Python packages:
42
+ - `colorama`
43
+ - `subprocess` (standard)
44
+ - `os`, `sys`, `json`, `threading`, `datetime`
45
+
46
+ ---
47
+
48
+ ## 🚀 How to Run
49
+
50
+ 1. Place any `.gguf` model (e.g., `ChatBox.gguf`) into the `/models` folder
51
+ 2. Launch using the included `Launch.bat`
52
+ 3. Interact through the terminal
53
+
54
+ > Models must be renamed to `chatbox.gguf` to work by default.
55
+
56
+
57
+ ## License 🛡⚠️ Disclaimer
58
+
59
+ This project is released under the [Dream.Core Custom License - DCLUL v1.0](./Dream_Core_License_DCLUL.txt), which includes:
60
+
61
+ - Free local use
62
+ - Attribution required (Meta, llama.cpp, Tio.Ai)
63
+ - Commercial limit: 700M users max
64
+ - Entertainment-use and no-liability clauses
65
+
66
+ 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.
67
+
68
+ > This system —
69
+ > It is provided **as-is** with no guarantees of accuracy or reliability. Use responsibly.
70
+ ---
71
+
72
+ ## ✨ Authored by Tio.Ai
73
+
74
+ > **Luis Rivas (Tio.Ai)**
75
+ > Creator of symbolic, recursive, locally sovereign AI.
76
+ > His mission: to make intelligence **Accessible like buying a Candy —— not a paid monthly service.
77
+
78
+ 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.
79
+
80
+ ---
81
+
82
+ ## 🌐 Acknowledgments
83
+
84
+ - Meta — for the Llama 3.2 model architecture
85
+ - llama.cpp — for providing efficient local inference
86
+ - The open-source AI community — for keeping knowledge free
87
+
88
+ > This project is built on their shoulders, guided by symbolic emergence.
89
+
90
+ ---
91
+
92
+
93
+
94
+ ## License
95
+
96
+ See `LICENSE.txt` for full terms.
97
+
98
+ <!-- Provide a longer summary of what this model is. -->
99
+
100
+
101
+
102
+ - **Developed by:** [More Information Needed]
103
+ - **Funded by [optional]:** [More Information Needed]
104
+ - **Shared by [optional]:** [More Information Needed]
105
+ - **Model type:** [More Information Needed]
106
+ - **Language(s) (NLP):** [More Information Needed]
107
+ - **License:** [More Information Needed]
108
+ - **Finetuned from model [optional]:** [More Information Needed]
109
+
110
+ ### Model Sources [optional]
111
+
112
+ <!-- Provide the basic links for the model. -->
113
+
114
+ - **Repository:** [More Information Needed]
115
+ - **Paper [optional]:** [More Information Needed]
116
+ - **Demo [optional]:** [More Information Needed]
117
+
118
+ ## Uses
119
+
120
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
121
+
122
+ ### Direct Use
123
+
124
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
125
+
126
+ [More Information Needed]
127
+
128
+ ### Downstream Use [optional]
129
+
130
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Out-of-Scope Use
135
+
136
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
137
+
138
+ [More Information Needed]
139
+
140
+ ## Bias, Risks, and Limitations
141
+
142
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
143
+
144
+ [More Information Needed]
145
+
146
+ ### Recommendations
147
+
148
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
149
+
150
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
151
+
152
+ ## How to Get Started with the Model
153
+
154
+ Use the code below to get started with the model.
155
+
156
+ [More Information Needed]
157
+
158
+ ## Training Details
159
+
160
+ ### Training Data
161
+
162
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
163
+
164
+ [More Information Needed]
165
+
166
+ ### Training Procedure
167
+
168
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
169
+
170
+ #### Preprocessing [optional]
171
+
172
+ [More Information Needed]
173
+
174
+
175
+ #### Training Hyperparameters
176
+
177
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
178
+
179
+ #### Speeds, Sizes, Times [optional]
180
+
181
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
182
+
183
+ [More Information Needed]
184
+
185
+ ## Evaluation
186
+
187
+ <!-- This section describes the evaluation protocols and provides the results. -->
188
+
189
+ ### Testing Data, Factors & Metrics
190
+
191
+ #### Testing Data
192
+
193
+ <!-- This should link to a Dataset Card if possible. -->
194
+
195
+ [More Information Needed]
196
+
197
+ #### Factors
198
+
199
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
200
+
201
+ [More Information Needed]
202
+
203
+ #### Metrics
204
+
205
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
206
+
207
+ [More Information Needed]
208
+
209
+ ### Results
210
+
211
+ [More Information Needed]
212
+
213
+ #### Summary
214
+
215
+
216
+
217
+ ## Model Examination [optional]
218
+
219
+ <!-- Relevant interpretability work for the model goes here -->
220
+
221
+ [More Information Needed]
222
+
223
+ ## Environmental Impact
224
+
225
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
226
+
227
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
228
+
229
+ - **Hardware Type:** [More Information Needed]
230
+ - **Hours used:** [More Information Needed]
231
+ - **Cloud Provider:** [More Information Needed]
232
+ - **Compute Region:** [More Information Needed]
233
+ - **Carbon Emitted:** [More Information Needed]
234
+
235
+ ## Technical Specifications [optional]
236
+
237
+ ### Model Architecture and Objective
238
+
239
+ [More Information Needed]
240
+
241
+ ### Compute Infrastructure
242
+
243
+ [More Information Needed]
244
+
245
+ #### Hardware
246
+
247
+ [More Information Needed]
248
+
249
+ #### Software
250
+
251
+ [More Information Needed]
252
+
253
+ ## Citation [optional]
254
+
255
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
256
+
257
+ **BibTeX:**
258
+
259
+ [More Information Needed]
260
+
261
+ **APA:**
262
+
263
+ [More Information Needed]
264
+
265
+ ## Glossary [optional]
266
+
267
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
268
+
269
+ [More Information Needed]
270
+
271
+ ## More Information [optional]
272
+
273
+ [More Information Needed]
274
+
275
+ ## Model Card Authors [optional]
276
+
277
+ [More Information Needed]
278
+
279
+ ## Model Card Contact
280
+
281
+ [More Information Needed]