regisss
/

llama2-70b-fused-qkv-mlperf

Text Generation

Model card Files Files and versions Community

regisss HF staff commited on Feb 14, 2024

Commit

ddcfa9e

•

1 Parent(s): d811de4

Update model_type

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -12,7 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 28672,
   "max_position_embeddings": 8192,
-  "model_type": "llama",
   "num_attention_heads": 64,
   "num_hidden_layers": 80,
   "num_key_value_heads": 8,

   "initializer_range": 0.02,
   "intermediate_size": 28672,
   "max_position_embeddings": 8192,
+  "model_type": "custom_llama",
   "num_attention_heads": 64,
   "num_hidden_layers": 80,
   "num_key_value_heads": 8,