Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,5 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9b808bfd5c4af1e368d95b372c491778c4c3e01f5fbfcd90fb51c1b27d0f30
+size 4972454376

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16dc83b786301a5dd6bb3f06b17c441fe14721afaf2dc803943ef8281291ed45
+size 4832048608

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4ed71c9a980cbe472e5f5fc8bfe87d635a9f3bc04c490b352873176c8b2980
+size 4832048656

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0d4a0e3852a965d1e2f1ee9f1b8264de6b1283851bc3060fd39d5f86d067f7
+size 4999855528

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1256a3c728430e5cfc7293da789b898e46ca5ea9cafbda784e9436dbe3d2de
+size 4832048672

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbff6633142c99d61a4287e61049177c82526c7295a8258027a3d6ee59ce598
+size 4832048672

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73aac17dc5253f04c1aef1a09e9d8b97c817af244e7d74ae05de166e6329f86
+size 3462482728

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 32762941440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

neuron-compiled-artifacts/0a2005d8ec0c38942a1a97c7740bc4b9/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3254b36ccc2a1ca1fef2dc50392d2aa13aede16af252a8e3dd2597f9a952ac5e
+size 79353803

neuron-compiled-artifacts/0a2005d8ec0c38942a1a97c7740bc4b9/neuron_config.json

@@ -0,0 +1,226 @@
+{
+  "_attn_implementation_autoset": false,
+  "_name_or_path": "Qwen/Qwen3-8B",
+  "add_cross_attention": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attribute_map": {},
+  "bad_words_ids": null,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 151643,
+  "chunk_size_feed_forward": 0,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": null,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": 151645,
+  "exponential_decay_length_penalty": null,
+  "finetuning_task": null,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "fused_spec_config": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "metadata": null,
+  "min_length": 0,
+  "model_type": "qwen3",
+  "neuron_config": {
+    "activation_quantization_type": null,
+    "allow_input_truncation": false,
+    "apply_seq_ids_mask": false,
+    "async_mode": false,
+    "attention_dp_degree": 1,
+    "attention_dtype": null,
+    "attn_block_cte_nki_kernel_enabled": false,
+    "attn_block_tkg_nki_kernel_cache_update": false,
+    "attn_block_tkg_nki_kernel_enabled": false,
+    "attn_cls": {
+      "__module__": "neuronx_distributed_inference.models.qwen3.modeling_qwen3",
+      "__name__": "NeuronQwen3Attention"
+    },
+    "attn_kernel_enabled": null,
+    "attn_tkg_builtin_kernel_enabled": false,
+    "attn_tkg_nki_kernel_enabled": false,
+    "batch_size": 1,
+    "bucket_n_active_tokens": false,
+    "buckets": [
+      8192
+    ],
+    "cast_type": "config",
+    "cc_pipeline_tiling_factor": 2,
+    "chunked_prefill_config": null,
+    "context_encoding_buckets": [
+      1024,
+      2048,
+      4096,
+      5120,
+      8000
+    ],
+    "cp_degree": 1,
+    "ctx_batch_size": 1,
+    "disable_kv_cache_tiling": false,
+    "draft_model_modules_to_not_convert": null,
+    "enable_bucketing": true,
+    "enable_eagle_draft_input_norm": false,
+    "enable_eagle_speculation": false,
+    "enable_fused_speculation": false,
+    "enable_long_context_mode": false,
+    "enable_output_completion_notifications": false,
+    "enable_spill_reload_dge": false,
+    "enable_token_tree": false,
+    "ep_degree": 1,
+    "expert_mlp_nki_kernel_enabled": null,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "fused_rmsnorm_skip_gamma": false,
+    "is_block_kv_layout": null,
+    "is_chunked_prefill": false,
+    "is_continuous_batching": true,
+    "is_eagle_draft": false,
+    "is_medusa": false,
+    "is_prefill_stage": null,
+    "is_prefix_caching": false,
+    "k_cache_transposed": false,
+    "kv_cache_batch_size": 1,
+    "kv_cache_padding_size": 0,
+    "kv_cache_quant": false,
+    "kv_cache_tiling": false,
+    "layer_boundary_markers": false,
+    "lm_head_pad": false,
+    "lm_head_pad_alignment_size": 1,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "lora_config": null,
+    "max_batch_size": 1,
+    "max_context_length": 8192,
+    "max_length": 8192,
+    "max_new_tokens": null,
+    "medusa_speculation_length": 0,
+    "medusa_tree": null,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "modules_to_not_convert": null,
+    "moe_fused_nki_kernel_enabled": null,
+    "n_active_tokens": 8192,
+    "n_positions": 8192,
+    "num_medusa_heads": 0,
+    "on_cpu": false,
+    "on_device_sampling_config": {
+      "deterministic": false,
+      "do_sample": false,
+      "dynamic": true,
+      "global_topk": 256,
+      "on_device_sampling_config": true,
+      "temperature": 1.0,
+      "top_k": 1,
+      "top_k_kernel_enabled": false,
+      "top_p": 1.0
+    },
+    "output_logits": false,
+    "overrides_torch_dtype": true,
+    "pa_block_size": 8192,
+    "pa_num_blocks": 1,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "prefix_buckets": null,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "qkv_kernel_fuse_residual_add": false,
+    "qkv_kernel_nbsd_layout": false,
+    "quantization_dtype": "int8",
+    "quantization_type": "per_tensor_symmetric",
+    "quantize_clamp_bound": Infinity,
+    "quantized": false,
+    "quantized_checkpoints_path": null,
+    "quantized_mlp_kernel_enabled": false,
+    "rmsnorm_quantize_kernel_enabled": false,
+    "router_topk_nki_kernel_enabled": null,
+    "rpl_reduce_dtype": null,
+    "save_sharded_checkpoint": false,
+    "scratchpad_page_size": null,
+    "seq_len": 8192,
+    "seq_len_threshold_for_cc_tiling": 16384,
+    "sequence_parallel_enabled": false,
+    "shared_mlp_nki_kernel_enabled": null,
+    "skip_sharding": false,
+    "skip_warmup": false,
+    "spec_batch_size": 1,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "tile_cc": false,
+    "tkg_batch_size": 1,
+    "token_generation_buckets": [
+      8192
+    ],
+    "token_tree_config": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false,
+    "weight_gather_seq_len_threshold": 32768,
+    "weights_to_skip_layout_optimization": [],
+    "world_size": 2
+  },
+  "no_repeat_ngram_size": 0,
+  "num_attention_heads": 32,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_cores_per_group": 1,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": null,
+  "prefix": null,
+  "problem_type": null,
+  "pruned_heads": {},
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict": true,
+  "return_dict_in_generate": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sep_token_id": null,
+  "sliding_window": null,
+  "suppress_tokens": null,
+  "task_specific_params": null,
+  "temperature": 1.0,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "transformers_version": "4.51.0",
+  "typical_p": 1.0,
+  "use_bfloat16": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuron-compiled-artifacts/37ee724f3e146a3c7d9d2ae94a51f278/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8890cc2bab772626613edfa8b26bd5b89fab2b2ec9f9439fd362d01eba7efe
+size 15442571

neuron-compiled-artifacts/37ee724f3e146a3c7d9d2ae94a51f278/neuron_config.json

@@ -0,0 +1,218 @@
+{
+  "_attn_implementation_autoset": false,
+  "_name_or_path": "Qwen/Qwen3-8B",
+  "add_cross_attention": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attribute_map": {},
+  "bad_words_ids": null,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 151643,
+  "chunk_size_feed_forward": 0,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": null,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": 151645,
+  "exponential_decay_length_penalty": null,
+  "finetuning_task": null,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "fused_spec_config": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "metadata": null,
+  "min_length": 0,
+  "model_type": "qwen3",
+  "neuron_config": {
+    "activation_quantization_type": null,
+    "allow_input_truncation": false,
+    "apply_seq_ids_mask": false,
+    "async_mode": false,
+    "attention_dp_degree": 1,
+    "attention_dtype": null,
+    "attn_block_cte_nki_kernel_enabled": false,
+    "attn_block_tkg_nki_kernel_cache_update": false,
+    "attn_block_tkg_nki_kernel_enabled": false,
+    "attn_cls": {
+      "__module__": "neuronx_distributed_inference.models.qwen3.modeling_qwen3",
+      "__name__": "NeuronQwen3Attention"
+    },
+    "attn_kernel_enabled": null,
+    "attn_tkg_builtin_kernel_enabled": false,
+    "attn_tkg_nki_kernel_enabled": false,
+    "batch_size": 1,
+    "bucket_n_active_tokens": false,
+    "buckets": [
+      128
+    ],
+    "cast_type": "config",
+    "cc_pipeline_tiling_factor": 2,
+    "chunked_prefill_config": null,
+    "context_encoding_buckets": null,
+    "cp_degree": 1,
+    "ctx_batch_size": 1,
+    "disable_kv_cache_tiling": false,
+    "draft_model_modules_to_not_convert": null,
+    "enable_bucketing": true,
+    "enable_eagle_draft_input_norm": false,
+    "enable_eagle_speculation": false,
+    "enable_fused_speculation": false,
+    "enable_long_context_mode": false,
+    "enable_output_completion_notifications": false,
+    "enable_spill_reload_dge": false,
+    "enable_token_tree": false,
+    "ep_degree": 1,
+    "expert_mlp_nki_kernel_enabled": null,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "fused_rmsnorm_skip_gamma": false,
+    "is_block_kv_layout": null,
+    "is_chunked_prefill": false,
+    "is_continuous_batching": true,
+    "is_eagle_draft": false,
+    "is_medusa": false,
+    "is_prefill_stage": null,
+    "is_prefix_caching": false,
+    "k_cache_transposed": false,
+    "kv_cache_batch_size": 1,
+    "kv_cache_padding_size": 0,
+    "kv_cache_quant": false,
+    "kv_cache_tiling": false,
+    "layer_boundary_markers": false,
+    "lm_head_pad": false,
+    "lm_head_pad_alignment_size": 1,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "lora_config": null,
+    "max_batch_size": 1,
+    "max_context_length": 128,
+    "max_length": 128,
+    "max_new_tokens": null,
+    "medusa_speculation_length": 0,
+    "medusa_tree": null,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "modules_to_not_convert": null,
+    "moe_fused_nki_kernel_enabled": null,
+    "n_active_tokens": 128,
+    "n_positions": 128,
+    "num_medusa_heads": 0,
+    "on_cpu": false,
+    "on_device_sampling_config": {
+      "deterministic": false,
+      "do_sample": false,
+      "dynamic": true,
+      "global_topk": 256,
+      "on_device_sampling_config": true,
+      "temperature": 1.0,
+      "top_k": 1,
+      "top_k_kernel_enabled": false,
+      "top_p": 1.0
+    },
+    "output_logits": false,
+    "overrides_torch_dtype": true,
+    "pa_block_size": 128,
+    "pa_num_blocks": 1,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "prefix_buckets": null,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "qkv_kernel_fuse_residual_add": false,
+    "qkv_kernel_nbsd_layout": false,
+    "quantization_dtype": "int8",
+    "quantization_type": "per_tensor_symmetric",
+    "quantize_clamp_bound": Infinity,
+    "quantized": false,
+    "quantized_checkpoints_path": null,
+    "quantized_mlp_kernel_enabled": false,
+    "rmsnorm_quantize_kernel_enabled": false,
+    "router_topk_nki_kernel_enabled": null,
+    "rpl_reduce_dtype": null,
+    "save_sharded_checkpoint": false,
+    "scratchpad_page_size": null,
+    "seq_len": 128,
+    "seq_len_threshold_for_cc_tiling": 16384,
+    "sequence_parallel_enabled": false,
+    "shared_mlp_nki_kernel_enabled": null,
+    "skip_sharding": false,
+    "skip_warmup": false,
+    "spec_batch_size": 1,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "tile_cc": false,
+    "tkg_batch_size": 1,
+    "token_generation_buckets": null,
+    "token_tree_config": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false,
+    "weight_gather_seq_len_threshold": 32768,
+    "weights_to_skip_layout_optimization": [],
+    "world_size": 2
+  },
+  "no_repeat_ngram_size": 0,
+  "num_attention_heads": 32,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_cores_per_group": 1,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": null,
+  "prefix": null,
+  "problem_type": null,
+  "pruned_heads": {},
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict": true,
+  "return_dict_in_generate": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sep_token_id": null,
+  "sliding_window": null,
+  "suppress_tokens": null,
+  "task_specific_params": null,
+  "temperature": 1.0,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "transformers_version": "4.51.0",
+  "typical_p": 1.0,
+  "use_bfloat16": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuron-compiled-artifacts/5a51556b3ef0a6dc53fb910b33a8c3c5/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ad30726e6c891ca6e4324649e2cac21fda8fcceafb9c16bbd06c36675785ed
+size 50921511

neuron-compiled-artifacts/5a51556b3ef0a6dc53fb910b33a8c3c5/neuron_config.json

@@ -0,0 +1,218 @@
+{
+  "_attn_implementation_autoset": false,
+  "_name_or_path": "Qwen/Qwen3-8B",
+  "add_cross_attention": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attribute_map": {},
+  "bad_words_ids": null,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 151643,
+  "chunk_size_feed_forward": 0,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": null,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": 151645,
+  "exponential_decay_length_penalty": null,
+  "finetuning_task": null,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "fused_spec_config": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "metadata": null,
+  "min_length": 0,
+  "model_type": "qwen3",
+  "neuron_config": {
+    "activation_quantization_type": null,
+    "allow_input_truncation": false,
+    "apply_seq_ids_mask": false,
+    "async_mode": false,
+    "attention_dp_degree": 1,
+    "attention_dtype": null,
+    "attn_block_cte_nki_kernel_enabled": false,
+    "attn_block_tkg_nki_kernel_cache_update": false,
+    "attn_block_tkg_nki_kernel_enabled": false,
+    "attn_cls": {
+      "__module__": "neuronx_distributed_inference.models.qwen3.modeling_qwen3",
+      "__name__": "NeuronQwen3Attention"
+    },
+    "attn_kernel_enabled": null,
+    "attn_tkg_builtin_kernel_enabled": false,
+    "attn_tkg_nki_kernel_enabled": false,
+    "batch_size": 8,
+    "bucket_n_active_tokens": false,
+    "buckets": [
+      1024
+    ],
+    "cast_type": "config",
+    "cc_pipeline_tiling_factor": 2,
+    "chunked_prefill_config": null,
+    "context_encoding_buckets": null,
+    "cp_degree": 1,
+    "ctx_batch_size": 1,
+    "disable_kv_cache_tiling": false,
+    "draft_model_modules_to_not_convert": null,
+    "enable_bucketing": true,
+    "enable_eagle_draft_input_norm": false,
+    "enable_eagle_speculation": false,
+    "enable_fused_speculation": false,
+    "enable_long_context_mode": false,
+    "enable_output_completion_notifications": false,
+    "enable_spill_reload_dge": false,
+    "enable_token_tree": false,
+    "ep_degree": 1,
+    "expert_mlp_nki_kernel_enabled": null,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "fused_rmsnorm_skip_gamma": false,
+    "is_block_kv_layout": null,
+    "is_chunked_prefill": false,
+    "is_continuous_batching": true,
+    "is_eagle_draft": false,
+    "is_medusa": false,
+    "is_prefill_stage": null,
+    "is_prefix_caching": false,
+    "k_cache_transposed": false,
+    "kv_cache_batch_size": 8,
+    "kv_cache_padding_size": 0,
+    "kv_cache_quant": false,
+    "kv_cache_tiling": false,
+    "layer_boundary_markers": false,
+    "lm_head_pad": false,
+    "lm_head_pad_alignment_size": 1,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "lora_config": null,
+    "max_batch_size": 8,
+    "max_context_length": 1024,
+    "max_length": 1024,
+    "max_new_tokens": null,
+    "medusa_speculation_length": 0,
+    "medusa_tree": null,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "modules_to_not_convert": null,
+    "moe_fused_nki_kernel_enabled": null,
+    "n_active_tokens": 1024,
+    "n_positions": 1024,
+    "num_medusa_heads": 0,
+    "on_cpu": false,
+    "on_device_sampling_config": {
+      "deterministic": false,
+      "do_sample": false,
+      "dynamic": true,
+      "global_topk": 256,
+      "on_device_sampling_config": true,
+      "temperature": 1.0,
+      "top_k": 1,
+      "top_k_kernel_enabled": false,
+      "top_p": 1.0
+    },
+    "output_logits": false,
+    "overrides_torch_dtype": true,
+    "pa_block_size": 1024,
+    "pa_num_blocks": 8,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "prefix_buckets": null,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "qkv_kernel_fuse_residual_add": false,
+    "qkv_kernel_nbsd_layout": false,
+    "quantization_dtype": "int8",
+    "quantization_type": "per_tensor_symmetric",
+    "quantize_clamp_bound": Infinity,
+    "quantized": false,
+    "quantized_checkpoints_path": null,
+    "quantized_mlp_kernel_enabled": false,
+    "rmsnorm_quantize_kernel_enabled": false,
+    "router_topk_nki_kernel_enabled": null,
+    "rpl_reduce_dtype": null,
+    "save_sharded_checkpoint": false,
+    "scratchpad_page_size": null,
+    "seq_len": 1024,
+    "seq_len_threshold_for_cc_tiling": 16384,
+    "sequence_parallel_enabled": false,
+    "shared_mlp_nki_kernel_enabled": null,
+    "skip_sharding": false,
+    "skip_warmup": false,
+    "spec_batch_size": 8,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "tile_cc": false,
+    "tkg_batch_size": 8,
+    "token_generation_buckets": null,
+    "token_tree_config": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false,
+    "weight_gather_seq_len_threshold": 32768,
+    "weights_to_skip_layout_optimization": [],
+    "world_size": 2
+  },
+  "no_repeat_ngram_size": 0,
+  "num_attention_heads": 32,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_cores_per_group": 1,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": null,
+  "prefix": null,
+  "problem_type": null,
+  "pruned_heads": {},
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict": true,
+  "return_dict_in_generate": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sep_token_id": null,
+  "sliding_window": null,
+  "suppress_tokens": null,
+  "task_specific_params": null,
+  "temperature": 1.0,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "transformers_version": "4.51.0",
+  "typical_p": 1.0,
+  "use_bfloat16": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuron-compiled-artifacts/8355fe7cbd21f34af07ddc6cad71c7af/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36af686c95660e8beeebdd12dbacac1ebd9cc7f4af66c2f1b265154b9c1671a3
+size 114961571

neuron-compiled-artifacts/8355fe7cbd21f34af07ddc6cad71c7af/neuron_config.json

@@ -0,0 +1,218 @@
+{
+  "_attn_implementation_autoset": false,
+  "_name_or_path": "Qwen/Qwen3-8B",
+  "add_cross_attention": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attribute_map": {},
+  "bad_words_ids": null,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 151643,
+  "chunk_size_feed_forward": 0,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": null,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": 151645,
+  "exponential_decay_length_penalty": null,
+  "finetuning_task": null,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "fused_spec_config": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "metadata": null,
+  "min_length": 0,
+  "model_type": "qwen3",
+  "neuron_config": {
+    "activation_quantization_type": null,
+    "allow_input_truncation": false,
+    "apply_seq_ids_mask": false,
+    "async_mode": false,
+    "attention_dp_degree": 1,
+    "attention_dtype": null,
+    "attn_block_cte_nki_kernel_enabled": false,
+    "attn_block_tkg_nki_kernel_cache_update": false,
+    "attn_block_tkg_nki_kernel_enabled": false,
+    "attn_cls": {
+      "__module__": "neuronx_distributed_inference.models.qwen3.modeling_qwen3",
+      "__name__": "NeuronQwen3Attention"
+    },
+    "attn_kernel_enabled": null,
+    "attn_tkg_builtin_kernel_enabled": false,
+    "attn_tkg_nki_kernel_enabled": false,
+    "batch_size": 1,
+    "bucket_n_active_tokens": false,
+    "buckets": [
+      8192
+    ],
+    "cast_type": "config",
+    "cc_pipeline_tiling_factor": 2,
+    "chunked_prefill_config": null,
+    "context_encoding_buckets": null,
+    "cp_degree": 1,
+    "ctx_batch_size": 1,
+    "disable_kv_cache_tiling": false,
+    "draft_model_modules_to_not_convert": null,
+    "enable_bucketing": true,
+    "enable_eagle_draft_input_norm": false,
+    "enable_eagle_speculation": false,
+    "enable_fused_speculation": false,
+    "enable_long_context_mode": false,
+    "enable_output_completion_notifications": false,
+    "enable_spill_reload_dge": false,
+    "enable_token_tree": false,
+    "ep_degree": 1,
+    "expert_mlp_nki_kernel_enabled": null,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "fused_rmsnorm_skip_gamma": false,
+    "is_block_kv_layout": null,
+    "is_chunked_prefill": false,
+    "is_continuous_batching": true,
+    "is_eagle_draft": false,
+    "is_medusa": false,
+    "is_prefill_stage": null,
+    "is_prefix_caching": false,
+    "k_cache_transposed": false,
+    "kv_cache_batch_size": 1,
+    "kv_cache_padding_size": 0,
+    "kv_cache_quant": false,
+    "kv_cache_tiling": false,
+    "layer_boundary_markers": false,
+    "lm_head_pad": false,
+    "lm_head_pad_alignment_size": 1,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "lora_config": null,
+    "max_batch_size": 1,
+    "max_context_length": 8192,
+    "max_length": 8192,
+    "max_new_tokens": null,
+    "medusa_speculation_length": 0,
+    "medusa_tree": null,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "modules_to_not_convert": null,
+    "moe_fused_nki_kernel_enabled": null,
+    "n_active_tokens": 8192,
+    "n_positions": 8192,
+    "num_medusa_heads": 0,
+    "on_cpu": false,
+    "on_device_sampling_config": {
+      "deterministic": false,
+      "do_sample": false,
+      "dynamic": true,
+      "global_topk": 256,
+      "on_device_sampling_config": true,
+      "temperature": 1.0,
+      "top_k": 1,
+      "top_k_kernel_enabled": false,
+      "top_p": 1.0
+    },
+    "output_logits": false,
+    "overrides_torch_dtype": true,
+    "pa_block_size": 8192,
+    "pa_num_blocks": 1,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "prefix_buckets": null,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "qkv_kernel_fuse_residual_add": false,
+    "qkv_kernel_nbsd_layout": false,
+    "quantization_dtype": "int8",
+    "quantization_type": "per_tensor_symmetric",
+    "quantize_clamp_bound": Infinity,
+    "quantized": false,
+    "quantized_checkpoints_path": null,
+    "quantized_mlp_kernel_enabled": false,
+    "rmsnorm_quantize_kernel_enabled": false,
+    "router_topk_nki_kernel_enabled": null,
+    "rpl_reduce_dtype": null,
+    "save_sharded_checkpoint": false,
+    "scratchpad_page_size": null,
+    "seq_len": 8192,
+    "seq_len_threshold_for_cc_tiling": 16384,
+    "sequence_parallel_enabled": false,
+    "shared_mlp_nki_kernel_enabled": null,
+    "skip_sharding": false,
+    "skip_warmup": false,
+    "spec_batch_size": 1,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "tile_cc": false,
+    "tkg_batch_size": 1,
+    "token_generation_buckets": null,
+    "token_tree_config": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false,
+    "weight_gather_seq_len_threshold": 32768,
+    "weights_to_skip_layout_optimization": [],
+    "world_size": 2
+  },
+  "no_repeat_ngram_size": 0,
+  "num_attention_heads": 32,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_cores_per_group": 1,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": null,
+  "prefix": null,
+  "problem_type": null,
+  "pruned_heads": {},
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict": true,
+  "return_dict_in_generate": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sep_token_id": null,
+  "sliding_window": null,
+  "suppress_tokens": null,
+  "task_specific_params": null,
+  "temperature": 1.0,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "transformers_version": "4.51.0",
+  "typical_p": 1.0,
+  "use_bfloat16": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuron-compiled-artifacts/a309ad36acab7b3ad63b41efc3065229/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ffbdab9844a5d09dca4f9affdf2a678105172e6b6d85219d858abcb898f651
+size 47198475

neuron-compiled-artifacts/a309ad36acab7b3ad63b41efc3065229/neuron_config.json

@@ -0,0 +1,218 @@
+{
+  "_attn_implementation_autoset": false,
+  "_name_or_path": "Qwen/Qwen3-8B",
+  "add_cross_attention": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attribute_map": {},
+  "bad_words_ids": null,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 151643,
+  "chunk_size_feed_forward": 0,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": null,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": 151645,
+  "exponential_decay_length_penalty": null,
+  "finetuning_task": null,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "fused_spec_config": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "metadata": null,
+  "min_length": 0,
+  "model_type": "qwen3",
+  "neuron_config": {
+    "activation_quantization_type": null,
+    "allow_input_truncation": false,
+    "apply_seq_ids_mask": false,
+    "async_mode": false,
+    "attention_dp_degree": 1,
+    "attention_dtype": null,
+    "attn_block_cte_nki_kernel_enabled": false,
+    "attn_block_tkg_nki_kernel_cache_update": false,
+    "attn_block_tkg_nki_kernel_enabled": false,
+    "attn_cls": {
+      "__module__": "neuronx_distributed_inference.models.qwen3.modeling_qwen3",
+      "__name__": "NeuronQwen3Attention"
+    },
+    "attn_kernel_enabled": null,
+    "attn_tkg_builtin_kernel_enabled": false,
+    "attn_tkg_nki_kernel_enabled": false,
+    "batch_size": 1,
+    "bucket_n_active_tokens": false,
+    "buckets": [
+      1024
+    ],
+    "cast_type": "config",
+    "cc_pipeline_tiling_factor": 2,
+    "chunked_prefill_config": null,
+    "context_encoding_buckets": null,
+    "cp_degree": 1,
+    "ctx_batch_size": 1,
+    "disable_kv_cache_tiling": false,
+    "draft_model_modules_to_not_convert": null,
+    "enable_bucketing": true,
+    "enable_eagle_draft_input_norm": false,
+    "enable_eagle_speculation": false,
+    "enable_fused_speculation": false,
+    "enable_long_context_mode": false,
+    "enable_output_completion_notifications": false,
+    "enable_spill_reload_dge": false,
+    "enable_token_tree": false,
+    "ep_degree": 1,
+    "expert_mlp_nki_kernel_enabled": null,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "fused_rmsnorm_skip_gamma": false,
+    "is_block_kv_layout": null,
+    "is_chunked_prefill": false,
+    "is_continuous_batching": true,
+    "is_eagle_draft": false,
+    "is_medusa": false,
+    "is_prefill_stage": null,
+    "is_prefix_caching": false,
+    "k_cache_transposed": false,
+    "kv_cache_batch_size": 1,
+    "kv_cache_padding_size": 0,
+    "kv_cache_quant": false,
+    "kv_cache_tiling": false,
+    "layer_boundary_markers": false,
+    "lm_head_pad": false,
+    "lm_head_pad_alignment_size": 1,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "lora_config": null,
+    "max_batch_size": 1,
+    "max_context_length": 1024,
+    "max_length": 1024,
+    "max_new_tokens": null,
+    "medusa_speculation_length": 0,
+    "medusa_tree": null,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "modules_to_not_convert": null,
+    "moe_fused_nki_kernel_enabled": null,
+    "n_active_tokens": 1024,
+    "n_positions": 1024,
+    "num_medusa_heads": 0,
+    "on_cpu": false,
+    "on_device_sampling_config": {
+      "deterministic": false,
+      "do_sample": false,
+      "dynamic": true,
+      "global_topk": 256,
+      "on_device_sampling_config": true,
+      "temperature": 1.0,
+      "top_k": 1,
+      "top_k_kernel_enabled": false,
+      "top_p": 1.0
+    },
+    "output_logits": false,
+    "overrides_torch_dtype": true,
+    "pa_block_size": 1024,
+    "pa_num_blocks": 1,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "prefix_buckets": null,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "qkv_kernel_fuse_residual_add": false,
+    "qkv_kernel_nbsd_layout": false,
+    "quantization_dtype": "int8",
+    "quantization_type": "per_tensor_symmetric",
+    "quantize_clamp_bound": Infinity,
+    "quantized": false,
+    "quantized_checkpoints_path": null,
+    "quantized_mlp_kernel_enabled": false,
+    "rmsnorm_quantize_kernel_enabled": false,
+    "router_topk_nki_kernel_enabled": null,
+    "rpl_reduce_dtype": null,
+    "save_sharded_checkpoint": false,
+    "scratchpad_page_size": null,
+    "seq_len": 1024,
+    "seq_len_threshold_for_cc_tiling": 16384,
+    "sequence_parallel_enabled": false,
+    "shared_mlp_nki_kernel_enabled": null,
+    "skip_sharding": false,
+    "skip_warmup": false,
+    "spec_batch_size": 1,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "tile_cc": false,
+    "tkg_batch_size": 1,
+    "token_generation_buckets": null,
+    "token_tree_config": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false,
+    "weight_gather_seq_len_threshold": 32768,
+    "weights_to_skip_layout_optimization": [],
+    "world_size": 2
+  },
+  "no_repeat_ngram_size": 0,
+  "num_attention_heads": 32,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_cores_per_group": 1,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": null,
+  "prefix": null,
+  "problem_type": null,
+  "pruned_heads": {},
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict": true,
+  "return_dict_in_generate": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sep_token_id": null,
+  "sliding_window": null,
+  "suppress_tokens": null,
+  "task_specific_params": null,
+  "temperature": 1.0,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "transformers_version": "4.51.0",
+  "typical_p": 1.0,
+  "use_bfloat16": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuron-compiled-artifacts/fa23794eeeac2b9917c8eb24c5fb6a2f/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b149420174f8e55959eb0437d50e71f3c01bc5ba05f4d69a320d133cb570e5c
+size 89716583

neuron-compiled-artifacts/fa23794eeeac2b9917c8eb24c5fb6a2f/neuron_config.json

@@ -0,0 +1,218 @@
+{
+  "_attn_implementation_autoset": false,
+  "_name_or_path": "Qwen/Qwen3-8B",
+  "add_cross_attention": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attribute_map": {},
+  "bad_words_ids": null,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 151643,
+  "chunk_size_feed_forward": 0,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": null,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": 151645,
+  "exponential_decay_length_penalty": null,
+  "finetuning_task": null,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "fused_spec_config": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "metadata": null,
+  "min_length": 0,
+  "model_type": "qwen3",
+  "neuron_config": {
+    "activation_quantization_type": null,
+    "allow_input_truncation": false,
+    "apply_seq_ids_mask": false,
+    "async_mode": false,
+    "attention_dp_degree": 1,
+    "attention_dtype": null,
+    "attn_block_cte_nki_kernel_enabled": false,
+    "attn_block_tkg_nki_kernel_cache_update": false,
+    "attn_block_tkg_nki_kernel_enabled": false,
+    "attn_cls": {
+      "__module__": "neuronx_distributed_inference.models.qwen3.modeling_qwen3",
+      "__name__": "NeuronQwen3Attention"
+    },
+    "attn_kernel_enabled": null,
+    "attn_tkg_builtin_kernel_enabled": false,
+    "attn_tkg_nki_kernel_enabled": false,
+    "batch_size": 8,
+    "bucket_n_active_tokens": false,
+    "buckets": [
+      4096
+    ],
+    "cast_type": "config",
+    "cc_pipeline_tiling_factor": 2,
+    "chunked_prefill_config": null,
+    "context_encoding_buckets": null,
+    "cp_degree": 1,
+    "ctx_batch_size": 1,
+    "disable_kv_cache_tiling": false,
+    "draft_model_modules_to_not_convert": null,
+    "enable_bucketing": true,
+    "enable_eagle_draft_input_norm": false,
+    "enable_eagle_speculation": false,
+    "enable_fused_speculation": false,
+    "enable_long_context_mode": false,
+    "enable_output_completion_notifications": false,
+    "enable_spill_reload_dge": false,
+    "enable_token_tree": false,
+    "ep_degree": 1,
+    "expert_mlp_nki_kernel_enabled": null,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "fused_rmsnorm_skip_gamma": false,
+    "is_block_kv_layout": null,
+    "is_chunked_prefill": false,
+    "is_continuous_batching": true,
+    "is_eagle_draft": false,
+    "is_medusa": false,
+    "is_prefill_stage": null,
+    "is_prefix_caching": false,
+    "k_cache_transposed": false,
+    "kv_cache_batch_size": 8,
+    "kv_cache_padding_size": 0,
+    "kv_cache_quant": false,
+    "kv_cache_tiling": false,
+    "layer_boundary_markers": false,
+    "lm_head_pad": false,
+    "lm_head_pad_alignment_size": 1,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "lora_config": null,
+    "max_batch_size": 8,
+    "max_context_length": 4096,
+    "max_length": 4096,
+    "max_new_tokens": null,
+    "medusa_speculation_length": 0,
+    "medusa_tree": null,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "modules_to_not_convert": null,
+    "moe_fused_nki_kernel_enabled": null,
+    "n_active_tokens": 4096,
+    "n_positions": 4096,
+    "num_medusa_heads": 0,
+    "on_cpu": false,
+    "on_device_sampling_config": {
+      "deterministic": false,
+      "do_sample": false,
+      "dynamic": true,
+      "global_topk": 256,
+      "on_device_sampling_config": true,
+      "temperature": 1.0,
+      "top_k": 1,
+      "top_k_kernel_enabled": false,
+      "top_p": 1.0
+    },
+    "output_logits": false,
+    "overrides_torch_dtype": true,
+    "pa_block_size": 4096,
+    "pa_num_blocks": 8,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "prefix_buckets": null,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "qkv_kernel_fuse_residual_add": false,
+    "qkv_kernel_nbsd_layout": false,
+    "quantization_dtype": "int8",
+    "quantization_type": "per_tensor_symmetric",
+    "quantize_clamp_bound": Infinity,
+    "quantized": false,
+    "quantized_checkpoints_path": null,
+    "quantized_mlp_kernel_enabled": false,
+    "rmsnorm_quantize_kernel_enabled": false,
+    "router_topk_nki_kernel_enabled": null,
+    "rpl_reduce_dtype": null,
+    "save_sharded_checkpoint": false,
+    "scratchpad_page_size": null,
+    "seq_len": 4096,
+    "seq_len_threshold_for_cc_tiling": 16384,
+    "sequence_parallel_enabled": false,
+    "shared_mlp_nki_kernel_enabled": null,
+    "skip_sharding": false,
+    "skip_warmup": false,
+    "spec_batch_size": 8,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "tile_cc": false,
+    "tkg_batch_size": 8,
+    "token_generation_buckets": null,
+    "token_tree_config": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false,
+    "weight_gather_seq_len_threshold": 32768,
+    "weights_to_skip_layout_optimization": [],
+    "world_size": 2
+  },
+  "no_repeat_ngram_size": 0,
+  "num_attention_heads": 32,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_cores_per_group": 1,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": null,
+  "prefix": null,
+  "problem_type": null,
+  "pruned_heads": {},
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict": true,
+  "return_dict_in_generate": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sep_token_id": null,
+  "sliding_window": null,
+  "suppress_tokens": null,
+  "task_specific_params": null,
+  "temperature": 1.0,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "transformers_version": "4.51.0",
+  "typical_p": 1.0,
+  "use_bfloat16": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}