Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json 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": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "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": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

genie_config.json

@@ -0,0 +1,58 @@
+{
+    "dialog": {
+        "version": 1,
+        "type": "basic",
+        "context": {
+            "version": 1,
+            "size": 4096,
+            "n-vocab": 151936,
+            "bos-token": 151643,
+            "eos-token": 151645
+        },
+        "sampler": {
+            "version": 1,
+            "seed": 42,
+            "temp": 0.8,
+            "top-k": 40,
+            "top-p": 0.95
+        },
+        "tokenizer": {
+            "version": 1,
+            "path": "tokenizer.json"
+        },
+        "engine": {
+            "version": 1,
+            "n-threads": 3,
+            "backend": {
+                "version": 1,
+                "type": "QnnHtp",
+                "QnnHtp": {
+                    "version": 1,
+                    "use-mmap": true,
+                    "spill-fill-bufsize": 0,
+                    "mmap-budget": 0,
+                    "poll": true,
+                    "cpu-mask": "0xe0",
+                    "kv-dim": 128,
+                    "pos-id-dim": 64,
+                    "allow-async-init": false,
+                    "rope-theta": 1000000
+                },
+                "extensions": "htp_backend_ext_config.json"
+            },
+            "model": {
+                "version": 1,
+                "type": "binary",
+                "binary": {
+                    "version": 1,
+                    "ctx-bins": [
+                        "qwen3_4b_part_1_of_4.bin",
+                        "qwen3_4b_part_2_of_4.bin",
+                        "qwen3_4b_part_3_of_4.bin",
+                        "qwen3_4b_part_4_of_4.bin"
+                    ]
+                }
+            }
+        }
+    }
+}

htp_backend_ext_config.json

@@ -0,0 +1 @@
+{"devices": [{"soc_model": 87, "dsp_arch": "v81", "cores": [{"core_id": 0, "perf_profile": "burst", "rpc_control_latency": 100}]}], "memory": {"mem_type": "shared_buffer"}, "context": {"weight_sharing_enabled": true}}

metadata.yaml

@@ -0,0 +1,3223 @@
+components:
+  ar128_cl4096_1_of_4:
+    inputs:
+      input_ids:
+        shape:
+        - 1
+        - 128
+        dtype: int32
+    outputs:
+      /model/model/embed_tokens/Gather_output_0:
+        shape:
+        - 1
+        - 128
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 7.197370679789425e-06
+          offset: -30800
+  ar128_cl4096_2_of_4:
+    inputs:
+      /model/model/embed_tokens/Gather_output_0:
+        shape:
+        - 1
+        - 128
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 7.197370679789425e-06
+          offset: -30800
+      attention_mask:
+        shape:
+        - 1
+        - 1
+        - 128
+        - 4096
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.0015259021896696422
+          offset: -65535
+      position_ids_cos:
+        shape:
+        - 1
+        - 1
+        - 128
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      position_ids_sin:
+        shape:
+        - 1
+        - 1
+        - 128
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      past_key_0_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 2.345790112112451
+          offset: -128
+      past_value_0_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.004396342855738843
+          offset: -128
+      past_key_1_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.4745758537232406
+          offset: -128
+      past_value_1_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.005273671820759773
+          offset: -128
+      past_key_2_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.20883603394031525
+          offset: -128
+      past_value_2_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.0066236164420843124
+          offset: -128
+      past_key_3_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.20998451113700867
+          offset: -128
+      past_value_3_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.009058302268385887
+          offset: -128
+      past_key_4_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.5082661185677596
+          offset: -128
+      past_value_4_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.010039279237389565
+          offset: -128
+      past_key_5_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.8604878703440269
+          offset: -128
+      past_value_5_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.011779437772929668
+          offset: -128
+      past_key_6_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.32763143224040353
+          offset: -128
+      past_value_6_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.015452229417860508
+          offset: -128
+      past_key_7_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2633135938268947
+          offset: -128
+      past_value_7_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.023205885663628578
+          offset: -128
+      past_key_8_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.4432932138442993
+          offset: -128
+      past_value_8_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.025590643286705017
+          offset: -128
+      past_key_9_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.198994809248316
+          offset: -128
+      past_value_9_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.02567124180495739
+          offset: -128
+      past_key_10_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.3400344252586365
+          offset: -128
+      past_value_10_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.047514863312244415
+          offset: -128
+      past_key_11_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.30140187421182946
+          offset: -128
+      past_value_11_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.029060301818246915
+          offset: -128
+    outputs:
+      /model/model/layers.11/Add_1_output_0:
+        shape:
+        - 1
+        - 128
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.2177089144874876
+          offset: -14531
+      past_key_0_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 2.345790112112451
+          offset: -128
+      past_value_0_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.004396342855738843
+          offset: -128
+      past_key_1_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.4745758537232406
+          offset: -128
+      past_value_1_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.005273671820759773
+          offset: -128
+      past_key_2_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.20883603394031525
+          offset: -128
+      past_value_2_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.0066236164420843124
+          offset: -128
+      past_key_3_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.20998451113700867
+          offset: -128
+      past_value_3_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.009058302268385887
+          offset: -128
+      past_key_4_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.5082661185677596
+          offset: -128
+      past_value_4_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.010039279237389565
+          offset: -128
+      past_key_5_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.8604878703440269
+          offset: -128
+      past_value_5_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.011779437772929668
+          offset: -128
+      past_key_6_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.32763143224040353
+          offset: -128
+      past_value_6_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.015452229417860508
+          offset: -128
+      past_key_7_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2633135938268947
+          offset: -128
+      past_value_7_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.023205885663628578
+          offset: -128
+      past_key_8_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.4432932138442993
+          offset: -128
+      past_value_8_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.025590643286705017
+          offset: -128
+      past_key_9_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.198994809248316
+          offset: -128
+      past_value_9_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.02567124180495739
+          offset: -128
+      past_key_10_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.3400344252586365
+          offset: -128
+      past_value_10_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.047514863312244415
+          offset: -128
+      past_key_11_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.30140187421182946
+          offset: -128
+      past_value_11_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.029060301818246915
+          offset: -128
+  ar128_cl4096_3_of_4:
+    inputs:
+      /model/model/layers.11/Add_1_output_0:
+        shape:
+        - 1
+        - 128
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.2177089144874876
+          offset: -14531
+      attention_mask:
+        shape:
+        - 1
+        - 1
+        - 128
+        - 4096
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.0015259021896696422
+          offset: -65535
+      position_ids_cos:
+        shape:
+        - 1
+        - 1
+        - 128
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      position_ids_sin:
+        shape:
+        - 1
+        - 1
+        - 128
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      past_key_12_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2443227916955948
+          offset: -128
+      past_value_12_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.028940375395647183
+          offset: -128
+      past_key_13_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2185003776249923
+          offset: -128
+      past_value_13_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17545437812805176
+          offset: -128
+      past_key_14_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2587217390537262
+          offset: -128
+      past_value_14_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.09416288137435913
+          offset: -128
+      past_key_15_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.18699947867806502
+          offset: -128
+      past_value_15_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2346538033072404
+          offset: -128
+      past_key_16_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2061757892370224
+          offset: -128
+      past_value_16_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19758310092715767
+          offset: -128
+      past_key_17_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17539973521795799
+          offset: -128
+      past_value_17_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.32720860838890076
+          offset: -128
+      past_key_18_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19263408690925657
+          offset: -128
+      past_value_18_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16426491925096887
+          offset: -128
+      past_key_19_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.21870377659797668
+          offset: -128
+      past_value_19_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06083845153568298
+          offset: -128
+      past_key_20_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.1891358345746994
+          offset: -128
+      past_value_20_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.05266200378537178
+          offset: -128
+      past_key_21_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19000622606652928
+          offset: -128
+      past_value_21_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06354268141618864
+          offset: -128
+      past_key_22_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.22853676974773407
+          offset: -128
+      past_value_22_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19043058156967163
+          offset: -128
+      past_key_23_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2349507489542323
+          offset: -128
+      past_value_23_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06769621090626153
+          offset: -128
+    outputs:
+      /model/model/layers.23/Add_1_output_0:
+        shape:
+        - 1
+        - 128
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.22199481461480505
+          offset: -14218
+      past_key_12_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2443227916955948
+          offset: -128
+      past_value_12_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.028940375395647183
+          offset: -128
+      past_key_13_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2185003776249923
+          offset: -128
+      past_value_13_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17545437812805176
+          offset: -128
+      past_key_14_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2587217390537262
+          offset: -128
+      past_value_14_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.09416288137435913
+          offset: -128
+      past_key_15_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.18699947867806502
+          offset: -128
+      past_value_15_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2346538033072404
+          offset: -128
+      past_key_16_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2061757892370224
+          offset: -128
+      past_value_16_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19758310092715767
+          offset: -128
+      past_key_17_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17539973521795799
+          offset: -128
+      past_value_17_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.32720860838890076
+          offset: -128
+      past_key_18_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19263408690925657
+          offset: -128
+      past_value_18_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16426491925096887
+          offset: -128
+      past_key_19_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.21870377659797668
+          offset: -128
+      past_value_19_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06083845153568298
+          offset: -128
+      past_key_20_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.1891358345746994
+          offset: -128
+      past_value_20_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.05266200378537178
+          offset: -128
+      past_key_21_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19000622606652928
+          offset: -128
+      past_value_21_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06354268141618864
+          offset: -128
+      past_key_22_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.22853676974773407
+          offset: -128
+      past_value_22_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19043058156967163
+          offset: -128
+      past_key_23_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2349507489542323
+          offset: -128
+      past_value_23_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06769621090626153
+          offset: -128
+  ar128_cl4096_4_of_4:
+    inputs:
+      /model/model/layers.23/Add_1_output_0:
+        shape:
+        - 1
+        - 128
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.22199481461480505
+          offset: -14218
+      attention_mask:
+        shape:
+        - 1
+        - 1
+        - 128
+        - 4096
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.0015259021896696422
+          offset: -65535
+      position_ids_cos:
+        shape:
+        - 1
+        - 1
+        - 128
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      position_ids_sin:
+        shape:
+        - 1
+        - 1
+        - 128
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      past_key_24_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2168474873219888
+          offset: -128
+      past_value_24_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.0993499606847763
+          offset: -128
+      past_key_25_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16338758170604706
+          offset: -128
+      past_value_25_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.08785130083560944
+          offset: -128
+      past_key_26_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17082346975803375
+          offset: -128
+      past_value_26_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.09179645448219119
+          offset: -128
+      past_key_27_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.15799155831336975
+          offset: -128
+      past_value_27_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.11564768105745316
+          offset: -128
+      past_key_28_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16321668850155327
+          offset: -128
+      past_value_28_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.12118262193334384
+          offset: -128
+      past_key_29_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.181901752948761
+          offset: -128
+      past_value_29_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.35103084534171997
+          offset: -128
+      past_key_30_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.18615905940532684
+          offset: -128
+      past_value_30_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.29017698764801025
+          offset: -128
+      past_key_31_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19037732481956482
+          offset: -128
+      past_value_31_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.3625663096510519
+          offset: -128
+      past_key_32_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.15537120789054812
+          offset: -128
+      past_value_32_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.45803920115072894
+          offset: -128
+      past_key_33_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17338245121512827
+          offset: -128
+      past_value_33_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.9015522754098487
+          offset: -128
+      past_key_34_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17443639039993286
+          offset: -128
+      past_value_34_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.8790855407714844
+          offset: -128
+      past_key_35_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 3968
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.35408836603164673
+          offset: -128
+      past_value_35_in:
+        shape:
+        - 8
+        - 1
+        - 3968
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.470033198595047
+          offset: -128
+    outputs:
+      logits:
+        shape:
+        - 1
+        - 128
+        - 151936
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.0013899723052105387
+          offset: -26872
+      past_key_24_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2168474873219888
+          offset: -128
+      past_value_24_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.0993499606847763
+          offset: -128
+      past_key_25_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16338758170604706
+          offset: -128
+      past_value_25_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.08785130083560944
+          offset: -128
+      past_key_26_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17082346975803375
+          offset: -128
+      past_value_26_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.09179645448219119
+          offset: -128
+      past_key_27_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.15799155831336975
+          offset: -128
+      past_value_27_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.11564768105745316
+          offset: -128
+      past_key_28_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16321668850155327
+          offset: -128
+      past_value_28_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.12118262193334384
+          offset: -128
+      past_key_29_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.181901752948761
+          offset: -128
+      past_value_29_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.35103084534171997
+          offset: -128
+      past_key_30_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.18615905940532684
+          offset: -128
+      past_value_30_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.29017698764801025
+          offset: -128
+      past_key_31_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19037732481956482
+          offset: -128
+      past_value_31_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.3625663096510519
+          offset: -128
+      past_key_32_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.15537120789054812
+          offset: -128
+      past_value_32_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.45803920115072894
+          offset: -128
+      past_key_33_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17338245121512827
+          offset: -128
+      past_value_33_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.9015522754098487
+          offset: -128
+      past_key_34_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17443639039993286
+          offset: -128
+      past_value_34_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.8790855407714844
+          offset: -128
+      past_key_35_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.35408836603164673
+          offset: -128
+      past_value_35_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.470033198595047
+          offset: -128
+  ar1_cl4096_1_of_4:
+    inputs:
+      input_ids:
+        shape:
+        - 1
+        - 1
+        dtype: int32
+    outputs:
+      /model/model/embed_tokens/Gather_output_0:
+        shape:
+        - 1
+        - 1
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 7.197370679789425e-06
+          offset: -30800
+  ar1_cl4096_2_of_4:
+    inputs:
+      /model/model/embed_tokens/Gather_output_0:
+        shape:
+        - 1
+        - 1
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 7.197370679789425e-06
+          offset: -30800
+      attention_mask:
+        shape:
+        - 1
+        - 1
+        - 1
+        - 4096
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.0015259021896696422
+          offset: -65535
+      position_ids_cos:
+        shape:
+        - 1
+        - 1
+        - 1
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      position_ids_sin:
+        shape:
+        - 1
+        - 1
+        - 1
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      past_key_0_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 2.345790112112451
+          offset: -128
+      past_value_0_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.004396342855738843
+          offset: -128
+      past_key_1_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.4745758537232406
+          offset: -128
+      past_value_1_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.005273671820759773
+          offset: -128
+      past_key_2_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.20883603394031525
+          offset: -128
+      past_value_2_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.0066236164420843124
+          offset: -128
+      past_key_3_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.20998451113700867
+          offset: -128
+      past_value_3_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.009058302268385887
+          offset: -128
+      past_key_4_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.5082661185677596
+          offset: -128
+      past_value_4_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.010039279237389565
+          offset: -128
+      past_key_5_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.8604878703440269
+          offset: -128
+      past_value_5_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.011779437772929668
+          offset: -128
+      past_key_6_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.32763143224040353
+          offset: -128
+      past_value_6_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.015452229417860508
+          offset: -128
+      past_key_7_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2633135938268947
+          offset: -128
+      past_value_7_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.023205885663628578
+          offset: -128
+      past_key_8_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.4432932138442993
+          offset: -128
+      past_value_8_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.025590643286705017
+          offset: -128
+      past_key_9_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.198994809248316
+          offset: -128
+      past_value_9_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.02567124180495739
+          offset: -128
+      past_key_10_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.3400344252586365
+          offset: -128
+      past_value_10_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.047514863312244415
+          offset: -128
+      past_key_11_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.30140187421182946
+          offset: -128
+      past_value_11_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.029060301818246915
+          offset: -128
+    outputs:
+      /model/model/layers.11/Add_1_output_0:
+        shape:
+        - 1
+        - 1
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.2177089144874876
+          offset: -14531
+      past_key_0_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 2.345790112112451
+          offset: -128
+      past_value_0_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.004396342855738843
+          offset: -128
+      past_key_1_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.4745758537232406
+          offset: -128
+      past_value_1_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.005273671820759773
+          offset: -128
+      past_key_2_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.20883603394031525
+          offset: -128
+      past_value_2_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.0066236164420843124
+          offset: -128
+      past_key_3_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.20998451113700867
+          offset: -128
+      past_value_3_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.009058302268385887
+          offset: -128
+      past_key_4_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.5082661185677596
+          offset: -128
+      past_value_4_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.010039279237389565
+          offset: -128
+      past_key_5_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.8604878703440269
+          offset: -128
+      past_value_5_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.011779437772929668
+          offset: -128
+      past_key_6_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.32763143224040353
+          offset: -128
+      past_value_6_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.015452229417860508
+          offset: -128
+      past_key_7_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2633135938268947
+          offset: -128
+      past_value_7_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.023205885663628578
+          offset: -128
+      past_key_8_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.4432932138442993
+          offset: -128
+      past_value_8_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.025590643286705017
+          offset: -128
+      past_key_9_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.198994809248316
+          offset: -128
+      past_value_9_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.02567124180495739
+          offset: -128
+      past_key_10_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.3400344252586365
+          offset: -128
+      past_value_10_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.047514863312244415
+          offset: -128
+      past_key_11_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.30140187421182946
+          offset: -128
+      past_value_11_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.029060301818246915
+          offset: -128
+  ar1_cl4096_3_of_4:
+    inputs:
+      /model/model/layers.11/Add_1_output_0:
+        shape:
+        - 1
+        - 1
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.2177089144874876
+          offset: -14531
+      attention_mask:
+        shape:
+        - 1
+        - 1
+        - 1
+        - 4096
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.0015259021896696422
+          offset: -65535
+      position_ids_cos:
+        shape:
+        - 1
+        - 1
+        - 1
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      position_ids_sin:
+        shape:
+        - 1
+        - 1
+        - 1
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      past_key_12_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2443227916955948
+          offset: -128
+      past_value_12_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.028940375395647183
+          offset: -128
+      past_key_13_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2185003776249923
+          offset: -128
+      past_value_13_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17545437812805176
+          offset: -128
+      past_key_14_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2587217390537262
+          offset: -128
+      past_value_14_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.09416288137435913
+          offset: -128
+      past_key_15_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.18699947867806502
+          offset: -128
+      past_value_15_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2346538033072404
+          offset: -128
+      past_key_16_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2061757892370224
+          offset: -128
+      past_value_16_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19758310092715767
+          offset: -128
+      past_key_17_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17539973521795799
+          offset: -128
+      past_value_17_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.32720860838890076
+          offset: -128
+      past_key_18_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19263408690925657
+          offset: -128
+      past_value_18_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16426491925096887
+          offset: -128
+      past_key_19_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.21870377659797668
+          offset: -128
+      past_value_19_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06083845153568298
+          offset: -128
+      past_key_20_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.1891358345746994
+          offset: -128
+      past_value_20_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.05266200378537178
+          offset: -128
+      past_key_21_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19000622606652928
+          offset: -128
+      past_value_21_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06354268141618864
+          offset: -128
+      past_key_22_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.22853676974773407
+          offset: -128
+      past_value_22_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19043058156967163
+          offset: -128
+      past_key_23_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2349507489542323
+          offset: -128
+      past_value_23_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06769621090626153
+          offset: -128
+    outputs:
+      /model/model/layers.23/Add_1_output_0:
+        shape:
+        - 1
+        - 1
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.22199481461480505
+          offset: -14218
+      past_key_12_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2443227916955948
+          offset: -128
+      past_value_12_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.028940375395647183
+          offset: -128
+      past_key_13_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2185003776249923
+          offset: -128
+      past_value_13_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17545437812805176
+          offset: -128
+      past_key_14_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2587217390537262
+          offset: -128
+      past_value_14_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.09416288137435913
+          offset: -128
+      past_key_15_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.18699947867806502
+          offset: -128
+      past_value_15_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2346538033072404
+          offset: -128
+      past_key_16_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2061757892370224
+          offset: -128
+      past_value_16_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19758310092715767
+          offset: -128
+      past_key_17_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17539973521795799
+          offset: -128
+      past_value_17_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.32720860838890076
+          offset: -128
+      past_key_18_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19263408690925657
+          offset: -128
+      past_value_18_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16426491925096887
+          offset: -128
+      past_key_19_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.21870377659797668
+          offset: -128
+      past_value_19_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06083845153568298
+          offset: -128
+      past_key_20_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.1891358345746994
+          offset: -128
+      past_value_20_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.05266200378537178
+          offset: -128
+      past_key_21_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19000622606652928
+          offset: -128
+      past_value_21_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06354268141618864
+          offset: -128
+      past_key_22_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.22853676974773407
+          offset: -128
+      past_value_22_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19043058156967163
+          offset: -128
+      past_key_23_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2349507489542323
+          offset: -128
+      past_value_23_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.06769621090626153
+          offset: -128
+  ar1_cl4096_4_of_4:
+    inputs:
+      /model/model/layers.23/Add_1_output_0:
+        shape:
+        - 1
+        - 1
+        - 2560
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.22199481461480505
+          offset: -14218
+      attention_mask:
+        shape:
+        - 1
+        - 1
+        - 1
+        - 4096
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.0015259021896696422
+          offset: -65535
+      position_ids_cos:
+        shape:
+        - 1
+        - 1
+        - 1
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      position_ids_sin:
+        shape:
+        - 1
+        - 1
+        - 1
+        - 64
+        dtype: uint16
+        quantization_parameters:
+          scale: 3.0518043793392844e-05
+          offset: -32768
+      past_key_24_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2168474873219888
+          offset: -128
+      past_value_24_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.0993499606847763
+          offset: -128
+      past_key_25_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16338758170604706
+          offset: -128
+      past_value_25_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.08785130083560944
+          offset: -128
+      past_key_26_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17082346975803375
+          offset: -128
+      past_value_26_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.09179645448219119
+          offset: -128
+      past_key_27_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.15799155831336975
+          offset: -128
+      past_value_27_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.11564768105745316
+          offset: -128
+      past_key_28_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16321668850155327
+          offset: -128
+      past_value_28_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.12118262193334384
+          offset: -128
+      past_key_29_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.181901752948761
+          offset: -128
+      past_value_29_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.35103084534171997
+          offset: -128
+      past_key_30_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.18615905940532684
+          offset: -128
+      past_value_30_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.29017698764801025
+          offset: -128
+      past_key_31_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19037732481956482
+          offset: -128
+      past_value_31_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.3625663096510519
+          offset: -128
+      past_key_32_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.15537120789054812
+          offset: -128
+      past_value_32_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.45803920115072894
+          offset: -128
+      past_key_33_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17338245121512827
+          offset: -128
+      past_value_33_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.9015522754098487
+          offset: -128
+      past_key_34_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17443639039993286
+          offset: -128
+      past_value_34_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.8790855407714844
+          offset: -128
+      past_key_35_in:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 4095
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.35408836603164673
+          offset: -128
+      past_value_35_in:
+        shape:
+        - 8
+        - 1
+        - 4095
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.470033198595047
+          offset: -128
+    outputs:
+      logits:
+        shape:
+        - 1
+        - 1
+        - 151936
+        dtype: uint16
+        quantization_parameters:
+          scale: 0.0013899723052105387
+          offset: -26872
+      past_key_24_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.2168474873219888
+          offset: -128
+      past_value_24_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.0993499606847763
+          offset: -128
+      past_key_25_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16338758170604706
+          offset: -128
+      past_value_25_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.08785130083560944
+          offset: -128
+      past_key_26_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17082346975803375
+          offset: -128
+      past_value_26_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.09179645448219119
+          offset: -128
+      past_key_27_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.15799155831336975
+          offset: -128
+      past_value_27_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.11564768105745316
+          offset: -128
+      past_key_28_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.16321668850155327
+          offset: -128
+      past_value_28_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.12118262193334384
+          offset: -128
+      past_key_29_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.181901752948761
+          offset: -128
+      past_value_29_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.35103084534171997
+          offset: -128
+      past_key_30_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.18615905940532684
+          offset: -128
+      past_value_30_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.29017698764801025
+          offset: -128
+      past_key_31_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.19037732481956482
+          offset: -128
+      past_value_31_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.3625663096510519
+          offset: -128
+      past_key_32_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.15537120789054812
+          offset: -128
+      past_value_32_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.45803920115072894
+          offset: -128
+      past_key_33_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17338245121512827
+          offset: -128
+      past_value_33_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.9015522754098487
+          offset: -128
+      past_key_34_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.17443639039993286
+          offset: -128
+      past_value_34_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.8790855407714844
+          offset: -128
+      past_key_35_out:
+        shape:
+        - 8
+        - 1
+        - 128
+        - 1
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.35408836603164673
+          offset: -128
+      past_value_35_out:
+        shape:
+        - 8
+        - 1
+        - 1
+        - 128
+        dtype: uint8
+        quantization_parameters:
+          scale: 0.470033198595047
+          offset: -128
+precision: w4a16
+runtime: genie

qwen3_4b_part_1_of_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e639c72438fe0dd130b654edfc72286a2e4bd4342c10b4e4a9658160fc14633a
+size 777973760

qwen3_4b_part_2_of_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed132983eba72ef3d0da064d27a5e5df77c3aa93a3b4ea9c1e8e1d4cfd1a381
+size 629985280

qwen3_4b_part_3_of_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4308eba2aef46493c4bc764e6f0a49330640756147b80632cec8392368c687e4
+size 630013952

qwen3_4b_part_4_of_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98a924fe148e05a009d140759ec76ed52cca0616621f869b3e53607b9e79465c
+size 1023483904

sample_prompt.txt

@@ -0,0 +1,5 @@
+<|im_start|>system
+You are a helpful AI assistant<|im_end|>
+<|im_start|>user
+What is gravity? Keep the answer under ten words.<|im_end|>
+<|im_start|>assistant

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "is_fast": true,
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

tool-versions.yaml

@@ -0,0 +1 @@
+qairt: 2.42.0.251225135753_193295