Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ short_description: Small, local models distilled from frontier teachers
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<p align="center">
|
| 12 |
-
<img src="https://thelabsource.com/
|
| 13 |
</p>
|
| 14 |
|
| 15 |
# Advanced Data Intelligence
|
|
@@ -23,7 +23,7 @@ Every model here is built end-to-end on theLAB hardware — no cloud training
|
|
| 23 |
**Links:** [Website](https://advanced-data-intelligence.com) · [theLAB](https://thelabsource.com) · [YouTube — Advanced Data Intelligence](https://www.youtube.com/@AdvancedDataIntelligence) · [YouTube — ADI Online](https://www.youtube.com/@adi_onlin3)
|
| 24 |
|
| 25 |
<p align="center">
|
| 26 |
-
<img src="https://thelabsource.com/
|
| 27 |
</p>
|
| 28 |
|
| 29 |
## Models
|
|
@@ -55,7 +55,7 @@ ollama run hf.co/AdvancedDataIntelligence/adi-qwen2.5-coder-7b-kimi2.7-code-GGUF
|
|
| 55 |
```
|
| 56 |
|
| 57 |
<p align="center">
|
| 58 |
-
<img src="https://thelabsource.com/
|
| 59 |
</p>
|
| 60 |
|
| 61 |
---
|
|
@@ -83,7 +83,7 @@ huggingface-cli download AdvancedDataIntelligence/adi-qwen3-8b-glm5.2-general-GG
|
|
| 83 |
Then point any llama.cpp-based runtime at the downloaded file.
|
| 84 |
|
| 85 |
<p align="center">
|
| 86 |
-
<img src="https://thelabsource.com/
|
| 87 |
</p>
|
| 88 |
|
| 89 |
## The approach
|
|
@@ -93,7 +93,7 @@ Then point any llama.cpp-based runtime at the downloaded file.
|
|
| 93 |
- **Open.** Apache-2.0 where the base license allows, with full training details on each model card so the work is reproducible.
|
| 94 |
|
| 95 |
<p align="center">
|
| 96 |
-
<img src="https://thelabsource.com/
|
| 97 |
</p>
|
| 98 |
|
| 99 |
---
|
|
@@ -112,7 +112,7 @@ Follow the org to catch them on release.
|
|
| 112 |
Models follow the pattern `adi-<base>-<size>-<teacher>-<purpose>` — so the name tells you the student base, its size, the teacher it learned from, and what it's tuned for.
|
| 113 |
|
| 114 |
<p align="center">
|
| 115 |
-
<img src="https://thelabsource.com/
|
| 116 |
</p>
|
| 117 |
|
| 118 |
*Built at [theLAB](https://thelabsource.com) — Learning. Algorithms. Breakthroughs.*
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<p align="center">
|
| 12 |
+
<img src="https://serve.thelabsource.com/u/hcKP4D.png" width="720" alt="Advanced Data Intelligence">
|
| 13 |
</p>
|
| 14 |
|
| 15 |
# Advanced Data Intelligence
|
|
|
|
| 23 |
**Links:** [Website](https://advanced-data-intelligence.com) · [theLAB](https://thelabsource.com) · [YouTube — Advanced Data Intelligence](https://www.youtube.com/@AdvancedDataIntelligence) · [YouTube — ADI Online](https://www.youtube.com/@adi_onlin3)
|
| 24 |
|
| 25 |
<p align="center">
|
| 26 |
+
<img src="https://serve.thelabsource.com/u/iSOrnI.png" width="700" alt="">
|
| 27 |
</p>
|
| 28 |
|
| 29 |
## Models
|
|
|
|
| 55 |
```
|
| 56 |
|
| 57 |
<p align="center">
|
| 58 |
+
<img src="https://serve.thelabsource.com/u/uSv2Lp.png" width="760" alt="ADI model lineup — size on disk">
|
| 59 |
</p>
|
| 60 |
|
| 61 |
---
|
|
|
|
| 83 |
Then point any llama.cpp-based runtime at the downloaded file.
|
| 84 |
|
| 85 |
<p align="center">
|
| 86 |
+
<img src="https://serve.thelabsource.com/u/T5Kdlg.png" width="700" alt="">
|
| 87 |
</p>
|
| 88 |
|
| 89 |
## The approach
|
|
|
|
| 93 |
- **Open.** Apache-2.0 where the base license allows, with full training details on each model card so the work is reproducible.
|
| 94 |
|
| 95 |
<p align="center">
|
| 96 |
+
<img src="https://serve.thelabsource.com/u/ih5dUC.png" width="760" alt="The ADI distillation pipeline">
|
| 97 |
</p>
|
| 98 |
|
| 99 |
---
|
|
|
|
| 112 |
Models follow the pattern `adi-<base>-<size>-<teacher>-<purpose>` — so the name tells you the student base, its size, the teacher it learned from, and what it's tuned for.
|
| 113 |
|
| 114 |
<p align="center">
|
| 115 |
+
<img src="https://serve.thelabsource.com/u/E0V8eW.png" width="560" alt="ADI">
|
| 116 |
</p>
|
| 117 |
|
| 118 |
*Built at [theLAB](https://thelabsource.com) — Learning. Algorithms. Breakthroughs.*
|