Update README.md
Browse files
README.md
CHANGED
|
@@ -101,6 +101,10 @@ Despite its tiny physical footprint, Atomight-V2.1-0.5B targets highly efficient
|
|
| 101 |
- **Training Paradigm:** GRPO reinforcement learning focusing on high-signal reasoning vectors instead of brute-force dataset scale.
|
| 102 |
- **Edge-Optimized:** Designed specifically for low-overhead mobile, local, and browser-based inference loops (Google Colab / Kaggle native workflow).
|
| 103 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
---
|
| 105 |
|
| 106 |
## 📊 Evaluation & Benchmark Results
|
|
|
|
| 101 |
- **Training Paradigm:** GRPO reinforcement learning focusing on high-signal reasoning vectors instead of brute-force dataset scale.
|
| 102 |
- **Edge-Optimized:** Designed specifically for low-overhead mobile, local, and browser-based inference loops (Google Colab / Kaggle native workflow).
|
| 103 |
|
| 104 |
+
Weighted/Imatrix Quants, and Static Quants by [mradermacher](https://huggingface.co/mradermacher) are available at:
|
| 105 |
+
https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-i1-GGUF
|
| 106 |
+
https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF
|
| 107 |
+
|
| 108 |
---
|
| 109 |
|
| 110 |
## 📊 Evaluation & Benchmark Results
|