Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,25 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
# Apriel-Nemotron-15b-Thinker
|
| 6 |
|
| 7 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/63d3095c2727d7888cbb54e2/Lt1t0tOO5emz1X23Azg-E.png" width="120" alt="thumbnail"/> `/ˈɑː.pri.əl/`
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
base_model:
|
| 4 |
+
- ServiceNow-AI/Apriel-Nemotron-15b-Thinker
|
| 5 |
+
library_name: exllamav2
|
| 6 |
---
|
| 7 |
+
# Apriel-Nemotron-15b-Thinker-exl2
|
| 8 |
+
Original model: [Apriel-Nemotron-15b-Thinker](https://huggingface.co/ServiceNow-AI/Apriel-Nemotron-15b-Thinker) by [ServiceNow-AI](https://huggingface.co/ServiceNow-AI)
|
| 9 |
+
|
| 10 |
+
## Quants
|
| 11 |
+
[4bpw h6 (main)](https://huggingface.co/cgus/Apriel-Nemotron-15b-Thinker-exl2/tree/main)
|
| 12 |
+
[4.5bpw h6](https://huggingface.co/cgus/Apriel-Nemotron-15b-Thinker-exl2/tree/4.5bpw-h6)
|
| 13 |
+
[5bpw h6](https://huggingface.co/cgus/Apriel-Nemotron-15b-Thinker-exl2/tree/5bpw-h6)
|
| 14 |
+
[6bpw h6](https://huggingface.co/cgus/Apriel-Nemotron-15b-Thinker-exl2/tree/6bpw-h6)
|
| 15 |
+
[8bpw h8](https://huggingface.co/cgus/Apriel-Nemotron-15b-Thinker-exl2/tree/8bpw-h8)
|
| 16 |
+
|
| 17 |
+
## Quantization notes
|
| 18 |
+
Made with Exllamav2 0.2.9 dev with default dataset.
|
| 19 |
+
It can be used with RTX GPU (Windows) or RTX/ROCm (Linux) with TabbyAPI or Text-Generation-WebUI.
|
| 20 |
+
It seems this model uses unusual thinking tags that aren't automatically recognized by frontends.
|
| 21 |
+
|
| 22 |
+
## Original model card
|
| 23 |
# Apriel-Nemotron-15b-Thinker
|
| 24 |
|
| 25 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/63d3095c2727d7888cbb54e2/Lt1t0tOO5emz1X23Azg-E.png" width="120" alt="thumbnail"/> `/ˈɑː.pri.əl/`
|