Spaces:
Configuration error
Configuration error
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# 🥪 OpenFacedSandwich
|
| 2 |
+
|
| 3 |
+
Welcome to **OpenFacedSandwich** — a slightly absurd collection of Danish AI models, tools, and experiments… layered like a proper smørrebrød.
|
| 4 |
+
|
| 5 |
+
We build things that are:
|
| 6 |
+
- open 🧑🍳
|
| 7 |
+
- layered 🧠
|
| 8 |
+
- occasionally overengineered 😏
|
| 9 |
+
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
## 🍞 What’s on the menu?
|
| 13 |
+
|
| 14 |
+
### 🧠 DaMorph
|
| 15 |
+
A collection of experimental models exploring **morphological segmentation for Danish NLP**.
|
| 16 |
+
|
| 17 |
+
👉 Because Danish words are long… and deserve to be sliced properly.
|
| 18 |
+
|
| 19 |
+
**Includes:**
|
| 20 |
+
- DA-MORPH-CEREBRAS
|
| 21 |
+
- DA-MORPH-LLAMA3.2
|
| 22 |
+
- DA-MIXED variants
|
| 23 |
+
- Tokenizers (yes, we slice at every layer)
|
| 24 |
+
|
| 25 |
---
|
| 26 |
+
|
| 27 |
+
### 🏥 DaMedSum
|
| 28 |
+
Danish medical summarization models trained on **LUMI HPC**.
|
| 29 |
+
|
| 30 |
+
👉 Turning long, complicated medical text into something (slightly) more digestible.
|
| 31 |
+
|
| 32 |
+
**Includes:**
|
| 33 |
+
- T5-large
|
| 34 |
+
- large / base / small variants
|
| 35 |
+
|
| 36 |
+
---
|
| 37 |
+
|
| 38 |
+
### 🔪 Tokenizers (a.k.a. precision slicing)
|
| 39 |
+
Because no good sandwich starts without proper slicing.
|
| 40 |
+
|
| 41 |
+
- Morphological tokenizers for Danish
|
| 42 |
+
- Built to explore how structure impacts understanding
|
| 43 |
+
|
| 44 |
---
|
| 45 |
|
| 46 |
+
## 🥓 Philosophy
|
| 47 |
+
|
| 48 |
+
Why “OpenFacedSandwich”?
|
| 49 |
+
|
| 50 |
+
Because:
|
| 51 |
+
- **Open-faced** → everything is visible → open source
|
| 52 |
+
- **Layers** → models, tokens, systems
|
| 53 |
+
- **Stacking** → how we actually build AI
|
| 54 |
+
|
| 55 |
+
👉 We don’t just build models
|
| 56 |
+
👉 we **assemble sandwiches**
|
| 57 |
+
|
| 58 |
+
---
|
| 59 |
+
|
| 60 |
+
## 😂 What to expect
|
| 61 |
+
|
| 62 |
+
- Serious experiments 🤓
|
| 63 |
+
- Slightly cursed ideas 😈
|
| 64 |
+
- Danish NLP in all its glory 🇩🇰
|
| 65 |
+
- Things that *probably* shouldn’t work… but do
|
| 66 |
+
|
| 67 |
+
---
|
| 68 |
+
|
| 69 |
+
## 🧑🍳 Contribute
|
| 70 |
+
|
| 71 |
+
Got a model? A tokenizer? A weird idea?
|
| 72 |
+
|
| 73 |
+
👉 Add a layer.
|
| 74 |
+
|
| 75 |
+
---
|
| 76 |
+
|
| 77 |
+
## ⚡ Slogan
|
| 78 |
+
|
| 79 |
+
**Open source never tasted this good.**
|