Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ This is a low restriction, creative roleplay and conversational reasoning model
|
|
| 11 |
|
| 12 |
I have distilled and quantized the model through GPTQ 4-bit model (W4A16), meaning it can run on most GPUs.
|
| 13 |
|
| 14 |
-
This model uses ChatML chat template and can think using "<think>" and "</think>" tokens.
|
| 15 |
|
| 16 |
Established by Staticaliza.
|
| 17 |
|
|
|
|
| 11 |
|
| 12 |
I have distilled and quantized the model through GPTQ 4-bit model (W4A16), meaning it can run on most GPUs.
|
| 13 |
|
| 14 |
+
This model uses ChatML chat template and can think using "\<think>" and "\</think>" tokens.
|
| 15 |
|
| 16 |
Established by Staticaliza.
|
| 17 |
|