openbmb
/

Eurus-70b-sft

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

ganqu commited on Apr 12

Commit

0557982

•

1 Parent(s): d962e51

fix length & rope

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -11,7 +11,7 @@
   "hidden_size": 8192,
   "initializer_range": 0.02,
   "intermediate_size": 28672,
-  "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 64,
   "num_hidden_layers": 80,
@@ -19,7 +19,7 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.35.0",

   "hidden_size": 8192,
   "initializer_range": 0.02,
   "intermediate_size": 28672,
+  "max_position_embeddings": 16384,
   "model_type": "llama",
   "num_attention_heads": 64,
   "num_hidden_layers": 80,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.35.0",