Upload Qwen3ForCausalLM

config.json

@@ -9,6 +9,10 @@
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
+  "layer_types": [
+    "full_attention",
+    "full_attention"
+  ],
   "max_position_embeddings": 32768,
   "max_window_layers": 28,
   "model_type": "qwen3",
@@ -18,10 +22,10 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
+  "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.51.2",
+  "transformers_version": "4.53.0.dev0",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151669

generation_config.json

@@ -1,4 +1,4 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.51.2"
+  "transformers_version": "4.53.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a7eaf7108d52a16a7ef827ac7314cb64177856d830599e301be10e6e97d7f0
+oid sha256:4dceab8a2e7e43a4bfb668ad054fbb39a2a22f1f51875e1d4a1d8df488900028
 size 9816064