QuixiAI
/

Step-3.5-Flash-int4-AutoRound

Text Generation

4-bit precision

Model card Files Files and versions

ehartford commited on 13 days ago

Commit

9b0e049

·

verified ·

1 Parent(s): 761339f

Update README.md

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -21,7 +21,6 @@ This model was quantized to **4-bit weights (INT4)** using AutoRound with iterat
 * **Weight precision**: INT4
 * **Format**: GPTQ
 * **Optimization iters**: 200
-* **RTN optimization**: Disabled
 Please follow the license and usage restrictions of the original base model.
@@ -30,7 +29,7 @@ Please follow the license and usage restrictions of the original base model.
 ## Author
 This quantized model was produced by **Eric Hartford**, creator of **Dolphin** and **Samantha**,
-founder of **QuixiAI**, and formerly of **Cognitive Computations**.
 ---

 * **Weight precision**: INT4
 * **Format**: GPTQ
 * **Optimization iters**: 200
 Please follow the license and usage restrictions of the original base model.
 ## Author
 This quantized model was produced by **Eric Hartford**, creator of **Dolphin** and **Samantha**,
+founder of **QuixiAI**, formerly **Cognitive Computations**.
 ---