ritterkraft commited on
Commit
acb3b38
Β·
verified Β·
1 Parent(s): 4074ced

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -13
README.md CHANGED
@@ -12,15 +12,27 @@ short_description: Small, local models distilled from frontier teachers
12
  <img src="http://serve.thelabsource.com/u/FhQgYP.gif" width="720" alt="Advanced Data Intelligence">
13
  </p>
14
 
15
- # Advanced Data Intelligence
16
 
17
- **Small, local, open models β€” distilled from frontier teachers.**
 
 
18
 
19
- ADI is a line of compact language models built at [theLAB](https://thelabsource.com) (*Learning. Algorithms. Breakthroughs.*). Each model is a **knowledge distillation**: a strong frontier "teacher" generates high-quality answers across thousands of prompts, and a small "student" model is fine-tuned to imitate them β€” producing a model that reasons and responds like something much larger, while staying small enough to run on a single consumer GPU.
 
 
20
 
21
- Every model here is built end-to-end on theLAB hardware β€” no cloud training β€” then quantized to GGUF and shipped ready to run in [Ollama](https://ollama.com) or any llama.cpp-based runtime.
 
 
22
 
23
- **Links:** [Website](https://advanced-data-intelligence.com) Β· [theLAB](https://thelabsource.com) Β· [YouTube β€” Advanced Data Intelligence](https://www.youtube.com/@AdvancedDataIntelligence) Β· [YouTube β€” ADI Online](https://www.youtube.com/@adi_onlin3)
 
 
 
 
 
 
24
 
25
  <p align="center">
26
  <img src="https://serve.thelabsource.com/u/PjCf8w.png" width="700" alt="">
@@ -58,17 +70,23 @@ ollama run hf.co/AdvancedDataIntelligence/adi-qwen2.5-coder-7b-kimi2.7-code-GGUF
58
  <img src="https://serve.thelabsource.com/u/uSv2Lp.png" width="760" alt="ADI model lineup β€” size on disk">
59
  </p>
60
 
61
- ## Try it live
62
 
63
- A hosted demo is available as a Hugging Face Space β€” chat with the model directly in your browser, no install required.
64
 
65
- <a href="https://huggingface.co/spaces/AdvancedDataIntelligence/adi-qwen3.5-4b-glm5.2-general-demo">
66
- <img src="https://serve.thelabsource.com/u/4Kb3iS.gif" alt="adi-qwen3.5-4b-glm5.2-general live demo" width="800">
67
- </a>
68
 
69
- [β–Ά Launch the demo](https://huggingface.co/spaces/AdvancedDataIntelligence/adi-qwen3.5-4b-glm5.2-general-demo)
 
 
 
 
70
 
71
- Chat with the model directly in your browser β€” no install required.
 
 
72
 
73
  ---
74
 
@@ -127,4 +145,6 @@ Models follow the pattern `adi-<base>-<size>-<teacher>-<purpose>` β€” so the nam
127
  <img src="https://serve.thelabsource.com/u/yZylMt.gif" width="560" alt="ADI">
128
  </p>
129
 
130
- *Built at [theLAB](https://thelabsource.com) β€” Learning. Algorithms. Breakthroughs.*
 
 
 
12
  <img src="http://serve.thelabsource.com/u/FhQgYP.gif" width="720" alt="Advanced Data Intelligence">
13
  </p>
14
 
15
+ <h1 align="center">Advanced Data Intelligence</h1>
16
 
17
+ <p align="center">
18
+ <strong>Small, local, open models β€” distilled from frontier teachers.</strong>
19
+ </p>
20
 
21
+ <p align="center">
22
+ ADI is a line of compact language models built at <a href="https://thelabsource.com">theLAB</a> (<em>Learning. Algorithms. Breakthroughs.</em>). Each model is a <strong>knowledge distillation</strong>: a strong frontier "teacher" generates high-quality answers across thousands of prompts, and a small "student" model is fine-tuned to imitate them β€” producing a model that reasons and responds like something much larger, while staying small enough to run on a single consumer GPU.
23
+ </p>
24
 
25
+ <p align="center">
26
+ Every model here is built end-to-end on theLAB hardware β€” no cloud training β€” then quantized to GGUF and shipped ready to run in <a href="https://ollama.com">Ollama</a> or any llama.cpp-based runtime.
27
+ </p>
28
 
29
+ <p align="center">
30
+ <strong>Links:</strong>
31
+ <a href="https://advanced-data-intelligence.com">Website</a> Β·
32
+ <a href="https://thelabsource.com">theLAB</a> Β·
33
+ <a href="https://www.youtube.com/@AdvancedDataIntelligence">YouTube β€” Advanced Data Intelligence</a> Β·
34
+ <a href="https://www.youtube.com/@adi_onlin3">YouTube β€” ADI Online</a>
35
+ </p>
36
 
37
  <p align="center">
38
  <img src="https://serve.thelabsource.com/u/PjCf8w.png" width="700" alt="">
 
70
  <img src="https://serve.thelabsource.com/u/uSv2Lp.png" width="760" alt="ADI model lineup β€” size on disk">
71
  </p>
72
 
73
+ ---
74
 
75
+ <h2 align="center">Try it live</h2>
76
 
77
+ <p align="center">
78
+ A hosted demo is available as a Hugging Face Space β€” chat with the model directly in your browser, no install required.
79
+ </p>
80
 
81
+ <p align="center">
82
+ <a href="https://huggingface.co/spaces/AdvancedDataIntelligence/adi-qwen3.5-4b-glm5.2-general-demo">
83
+ <img src="https://serve.thelabsource.com/u/4Kb3iS.gif" alt="adi-qwen3.5-4b-glm5.2-general live demo" width="800">
84
+ </a>
85
+ </p>
86
 
87
+ <p align="center">
88
+ <a href="https://huggingface.co/spaces/AdvancedDataIntelligence/adi-qwen3.5-4b-glm5.2-general-demo">β–Ά Launch the demo</a>
89
+ </p>
90
 
91
  ---
92
 
 
145
  <img src="https://serve.thelabsource.com/u/yZylMt.gif" width="560" alt="ADI">
146
  </p>
147
 
148
+ <p align="center">
149
+ <em>Built at <a href="https://thelabsource.com">theLAB</a> β€” Learning. Algorithms. Breakthroughs.</em>
150
+ </p>