mertunsal
/

Qwen2.5-Math-1.5B-Instruct

Text Generation

text-generation-inference

Model card Files Files and versions

mertunsal commited on Apr 8, 2025

Commit

2fa4843

·

verified ·

1 Parent(s): b694498

Update config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -9,14 +9,14 @@
   "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,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
-  "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",

   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
+  "max_position_embeddings": 16384,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
+  "rope_theta": 100000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",