mattshumer
/

Meta-Llama-3-8B-Instruct-LongTest

Text Generation

text-generation-inference

Model card Files Files and versions

mattshumer commited on Apr 23, 2024

Commit

bf96966

·

verified ·

1 Parent(s): 3d60861

Update config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -10,7 +10,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -18,7 +18,7 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0.dev0",

   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
+  "max_position_embeddings": 32000,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 2000000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0.dev0",