pruna-test
/

qwen3_coder_tiny

Text Generation

Model card Files Files and versions

loulou2 commited on 27 days ago

Commit

6d0fe22

·

verified ·

1 Parent(s): 8f79584

Upload Qwen3MoeForCausalLM

Files changed (2) hide show

config.json +3 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -13,15 +13,15 @@
   "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,

   "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,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2a8eb2980eabd5dd5cf527e30000c1294432b6b7d991a0e1ee309358c1ef76
-size 2867888144

 version https://git-lfs.github.com/spec/v1
+oid sha256:939af8f8198e282063fb1e5f4d13eef59cddb50b39a52f5c0b77245c7b9fea21
+size 2866970640