nm-testing
/

Llama-3.1-8B-Instruct-QKV-Cache-FP8

krishnateja95 commited on Nov 11, 2025

Commit

29cdcb8

verified ·

1 Parent(s): ad27475

Upload folder using huggingface_hub

Files changed (1) hide show

config.json CHANGED Viewed

@@ -12,7 +12,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,

   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,