Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,25 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
-
-
|
| 4 |
license: mit
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
# Join our Discord! https://discord.gg/BeaverAI
|
| 7 |
## More than 6000 members of helpful, LLM enthusiasts! A hub for players and makers alike!
|
| 8 |
---
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
+
- TheDrummer/Snowpiercer-15B-v2
|
| 4 |
license: mit
|
| 5 |
---
|
| 6 |
+
# Snowpiercer-15B-v2-exl2
|
| 7 |
+
Original model: [Snowpiercer-15B-v2](https://huggingface.co/TheDrummer/Snowpiercer-15B-v2) by [TheDrummer](https://huggingface.co/TheDrummer/Snowpiercer-15B-v2)
|
| 8 |
+
Based on: [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/Snowpiercer-15B-v2-exl2/tree/main)
|
| 12 |
+
[4.5bpw h6](https://huggingface.co/cgus/Snowpiercer-15B-v2-exl2/tree/4.5bpw-h6)
|
| 13 |
+
[5bpw h6](https://huggingface.co/cgus/Snowpiercer-15B-v2-exl2/tree/5bpw-h6)
|
| 14 |
+
[6bpw h6](https://huggingface.co/cgus/Snowpiercer-15B-v2-exl2/tree/6bpw-h6)
|
| 15 |
+
[8bpw h8](https://huggingface.co/cgus/Snowpiercer-15B-v2-exl2/tree/8bpw-h8)
|
| 16 |
+
|
| 17 |
+
## Quantization notes
|
| 18 |
+
Made with Exllamav2 0.3.1 with default dataset.
|
| 19 |
+
These quants require RTX GPU on Windows or RTX/ROCm GPU on Linux and can be used with TabbyAPI or Text-Generation-WebUI.
|
| 20 |
+
They require to be fully loaded into your GPU, if you have to rely on system RAM then GGUF quants is a better choice.
|
| 21 |
+
|
| 22 |
+
# Original model card
|
| 23 |
# Join our Discord! https://discord.gg/BeaverAI
|
| 24 |
## More than 6000 members of helpful, LLM enthusiasts! A hub for players and makers alike!
|
| 25 |
---
|