TheBloke
/

Llama-2-70B-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

TheBloke commited on Jul 25, 2023

Commit

ac790dc

•

1 Parent(s): 0d8f18c

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -9,7 +9,7 @@
     "initializer_range": 0.02,
     "intermediate_size": 28672,
     "max_length": 4096,
-    "max_position_embeddings": 2048,
     "model_type": "llama",
     "num_attention_heads": 64,
     "num_hidden_layers": 80,

     "initializer_range": 0.02,
     "intermediate_size": 28672,
     "max_length": 4096,
+    "max_position_embeddings": 4096,
     "model_type": "llama",
     "num_attention_heads": 64,
     "num_hidden_layers": 80,