lordspline
/

qwen-pruned-165m

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

lordspline commited on Jun 25

Commit

0768d3f

•

1 Parent(s): 18c9d9f

Update config.json

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Qwen/Qwen2-0.5B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -11,10 +11,10 @@
   "initializer_range": 0.02,
   "intermediate_size": 4864,
   "max_position_embeddings": 131072,
-  "max_window_layers": 24,
   "model_type": "qwen2",
   "num_attention_heads": 14,
-  "num_hidden_layers": 24,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,

 {
+  "_name_or_path": "lordspline/qwen-pruned-165m",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "initializer_range": 0.02,
   "intermediate_size": 4864,
   "max_position_embeddings": 131072,
+  "max_window_layers": 2,
   "model_type": "qwen2",
   "num_attention_heads": 14,
+  "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,