Spaces:
Running
Running
Add organization card content
#1
by VertexAIco - opened
README.md
CHANGED
|
@@ -7,4 +7,22 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
## Vertex AGI
|
| 11 |
+
|
| 12 |
+
Small, focused fine-tunes and distillations, built end-to-end — data generation, training, evaluation, and publishing — on consumer hardware.
|
| 13 |
+
|
| 14 |
+
### Model families
|
| 15 |
+
|
| 16 |
+
| Family | Base | Focus |
|
| 17 |
+
|---|---|---|
|
| 18 |
+
| **Amethyst** | Gemma 3 4B / Llama 3.1 8B | General-purpose chat & instruction-following |
|
| 19 |
+
| **Copal** | Gemma 3 4B IT | Agentic, tool-calling |
|
| 20 |
+
| **Prism Creative** | Qwen3-4B | Creative writing, distilled from GLM 5.2 |
|
| 21 |
+
| **Prism Roleplay** | Qwen3-8B | Character roleplay, distilled from GLM 5.2 / Nemotron-3-Nano |
|
| 22 |
+
|
| 23 |
+
Every model repo ships both **MLX** and **GGUF** formats in one place, so it runs on Apple Silicon (`mlx-lm`) or anywhere `llama.cpp` and its ecosystem (Ollama, LM Studio, etc.) reach.
|
| 24 |
+
|
| 25 |
+
### Links
|
| 26 |
+
|
| 27 |
+
- [Models](https://huggingface.co/VertexAGI?sort_models=created#models)
|
| 28 |
+
- [Datasets](https://huggingface.co/VertexAGI?sort_models=created#datasets)
|