winglian
/

Meta-Llama-3-8B-1M

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

winglian commited on Apr 30

Commit

e2fb9fc

•

1 Parent(s): b94b243

update context len after merging

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -11,7 +11,7 @@
   "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,
@@ -19,7 +19,7 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",

   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
+  "max_position_embeddings": 1048576,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 2804339835.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",