pruna-test
/

qwen3_coder_tiny

Text Generation

Model card Files Files and versions

loulou2 commited on 11 days ago

Commit

8f79584

·

verified ·

1 Parent(s): ea55fd0

Update config.json

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -13,15 +13,15 @@
   "initializer_range": 0.02,
   "intermediate_size": 6144,
   "max_position_embeddings": 262144,
-  "max_window_layers": 48,
   "mlp_only_layers": [],
   "model_type": "qwen3_moe",
   "moe_intermediate_size": 768,
   "norm_topk_prob": true,
   "num_attention_heads": 32,
-  "num_experts": 128,
   "num_experts_per_tok": 8,
-  "num_hidden_layers": 48,
   "num_key_value_heads": 4,
   "output_router_logits": false,
   "rms_norm_eps": 1e-06,

   "initializer_range": 0.02,
   "intermediate_size": 6144,
   "max_position_embeddings": 262144,
+  "max_window_layers": 1,
   "mlp_only_layers": [],
   "model_type": "qwen3_moe",
   "moe_intermediate_size": 768,
   "norm_topk_prob": true,
   "num_attention_heads": 32,
+  "num_experts": 16,
   "num_experts_per_tok": 8,
+  "num_hidden_layers": 1,
   "num_key_value_heads": 4,
   "output_router_logits": false,
   "rms_norm_eps": 1e-06,