nvidia
/

OpenReasoning-Nemotron-1.5B

Text Generation

text-generation-inference

Model card Files Files and versions

stoshniwal commited on Jul 23

Commit

38495aa

·

verified ·

1 Parent(s): 83d1fe8

Update genselect_hf.py

Files changed (1) hide show

genselect_hf.py +1 -1

genselect_hf.py CHANGED Viewed

@@ -106,7 +106,7 @@ doors) in a cycle is also 120. This maximum is achievable by removing one black
 ]
-MODEL_NAME = "nvidia/OpenReasoning-Nemotron-14B"
 MAX_NEW_TOKENS = 32000

 ]
+MODEL_NAME = "nvidia/OpenReasoning-Nemotron-1.5B"
 MAX_NEW_TOKENS = 32000