mlx-community
/

gemma-3-27b-it-4bit-DWQ

Text Generation

4-bit precision

Model card Files Files and versions

Update config.json

#2

by olegshulyakov - opened May 23

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

Files changed (1) hide show

config.json +1 -0

config.json CHANGED Viewed

@@ -24,6 +24,7 @@
         "head_dim": 128,
         "hidden_size": 5376,
         "intermediate_size": 21504,
         "model_type": "gemma3_text",
         "num_attention_heads": 32,
         "num_hidden_layers": 62,

         "head_dim": 128,
         "hidden_size": 5376,
         "intermediate_size": 21504,
+        "max_position_embeddings": 131072,
         "model_type": "gemma3_text",
         "num_attention_heads": 32,
         "num_hidden_layers": 62,