mlx-community
/

Llama-4-Scout-17B-16E-Instruct-4bit

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

awni commited on May 3

Commit

f89d3eb

·

verified ·

1 Parent(s): 93eb5fb

Update config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -139,8 +139,8 @@
         "num_hidden_layers": 48,
         "num_attention_heads": 40,
         "rope_scaling": {
-            "factor": 8.0,
-            "high_freq_factor": 4.0,
             "low_freq_factor": 1.0,
             "original_max_position_embeddings": 8192,
             "rope_type": "llama3"

         "num_hidden_layers": 48,
         "num_attention_heads": 40,
         "rope_scaling": {
+            "factor": 16.0,
+            "high_freq_factor": 1.0,
             "low_freq_factor": 1.0,
             "original_max_position_embeddings": 8192,
             "rope_type": "llama3"