Update README.md
Browse files
README.md
CHANGED
|
@@ -13,8 +13,6 @@ It can chat like a human (only when configured correctly)!
|
|
| 13 |
|
| 14 |
I have distilled and quantized the model through GPTQ 4-bit model (W4A16), meaning it can run on most GPUs.
|
| 15 |
|
| 16 |
-
This model can think using "<think>" and "</think>" tokens.
|
| 17 |
-
|
| 18 |
Established by Staticaliza.
|
| 19 |
|
| 20 |
# vLLM: Use Instruction
|
|
|
|
| 13 |
|
| 14 |
I have distilled and quantized the model through GPTQ 4-bit model (W4A16), meaning it can run on most GPUs.
|
| 15 |
|
|
|
|
|
|
|
| 16 |
Established by Staticaliza.
|
| 17 |
|
| 18 |
# vLLM: Use Instruction
|