prima02
/

Qwen2.5-Math-1.5B-Instruct

Text Generation

text-generation-inference

Model card Files Files and versions

Phu Nguyen commited on Mar 6

Commit

9e8efe9

·

verified ·

1 Parent(s): db66712

Update config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -10,7 +10,7 @@
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
-  "max_position_embeddings": 4096,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
@@ -18,7 +18,7 @@
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",

   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
+  "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",