Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# pipe-agent-v6
|
| 2 |
+
|
| 3 |
+
Screenpipe pipe agent v6 — fine-tuned Qwen3.5-9B with **vision enabled**.
|
| 4 |
+
|
| 5 |
+
- Base: Qwen/Qwen3.5-9B (natively multimodal)
|
| 6 |
+
- Training: LoRA r=64, alpha=128, 3 epochs, 7.8K examples
|
| 7 |
+
- Eval loss: 0.3210
|
| 8 |
+
- Vision tower frozen during training (pretrained weights preserved)
|
| 9 |
+
- See [GGUF version](https://huggingface.co/screenpipe/pipe-agent-v6-GGUF)
|