nm-testing
/

DeepSeek-R1-Distill-Qwen-32B-NVFP4

Text Generation

8-bit precision

compressed-tensors

Model card Files Files and versions

nm-research commited on Oct 29, 2025

Commit

83b82c0

·

verified ·

1 Parent(s): 1aba6ea

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -232,7 +232,7 @@ model_parameters:
   generation_parameters:
     seed: 42
     temperature: 0.6
-    top_k: 20
     top_p: 0.95
     min_p: 0.0
     max_new_tokens: 32768

   generation_parameters:
     seed: 42
     temperature: 0.6
+    top_k: 50
     top_p: 0.95
     min_p: 0.0
     max_new_tokens: 32768