Upload 33 files

.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

added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

config.json

@@ -0,0 +1,2613 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "Phi4MMForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "audio_processor": {
+    "config": {
+      "activation": "swish",
+      "activation_checkpointing": "",
+      "attention_dim": 1024,
+      "attention_heads": 16,
+      "batch_norm": false,
+      "bias_in_glu": true,
+      "causal": true,
+      "chunk_size": -1,
+      "cnn_layer_norm": true,
+      "conv_activation": "swish",
+      "conv_glu_type": "swish",
+      "depthwise_multiplier": 1,
+      "depthwise_seperable_out_channel": 1024,
+      "dropout_rate": 0.0,
+      "encoder_embedding_config": {
+        "input_size": 80
+      },
+      "ext_pw_kernel_size": 1,
+      "ext_pw_out_channel": 1024,
+      "input_layer": "nemo_conv",
+      "input_size": 80,
+      "kernel_size": 3,
+      "left_chunk": 18,
+      "linear_units": 1536,
+      "nemo_conv_settings": {
+        "conv_channels": 1024
+      },
+      "num_blocks": 24,
+      "relative_attention_bias_args": {
+        "t5_bias_max_distance": 500,
+        "type": "t5"
+      },
+      "time_reduction": 8
+    },
+    "name": "cascades"
+  },
+  "auto_map": {
+    "AutoConfig": "configuration_phi4mm.Phi4MMConfig",
+    "AutoModelForCausalLM": "microsoft/phi-4-multimodal-instruct--modeling_phi4mm.Phi4MMForCausalLM",
+    "AutoTokenizer": "microsoft/phi-4-multimodal-instruct--Xenova/gpt-4o"
+  },
+  "bos_token_id": 199999,
+  "embd_layer": {
+    "audio_embd_layer": {
+      "compression_rate": 8,
+      "downsample_rate": 1,
+      "embedding_cls": "audio",
+      "enable_gradient_checkpointing": true,
+      "projection_cls": "mlp",
+      "use_conv_downsample": false,
+      "use_qformer": false
+    },
+    "embedding_cls": "image_audio",
+    "image_embd_layer": {
+      "crop_size": 448,
+      "embedding_cls": "tune_image",
+      "enable_gradient_checkpointing": true,
+      "hd_transform_order": "sub_glb",
+      "image_token_compression_cls": "avg_pool_2d",
+      "projection_cls": "mlp",
+      "use_hd_transform": true,
+      "with_learnable_separator": true
+    }
+  },
+  "embd_pdrop": 0.0,
+  "eos_token_id": 199999,
+  "full_attn_mod": 1,
+  "glb_GN": [
+    [
+      [
+        0.0240478515625,
+        -0.03466796875,
+        -0.0201416015625,
+        0.0208740234375,
+        -0.0042724609375,
+        -0.034423828125,
+        0.01043701171875,
+        -0.03955078125,
+        -0.0103759765625,
+        0.0791015625,
+        -0.0225830078125,
+        0.0174560546875,
+        0.006622314453125,
+        -0.003143310546875,
+        0.0272216796875,
+        0.0400390625,
+        0.0166015625,
+        -0.034912109375,
+        0.015869140625,
+        -0.021728515625,
+        -0.0106201171875,
+        0.0400390625,
+        0.0081787109375,
+        -0.009521484375,
+        0.0107421875,
+        0.000499725341796875,
+        0.0439453125,
+        -0.02734375,
+        0.0179443359375,
+        -0.012451171875,
+        0.042724609375,
+        0.00043487548828125,
+        -0.00213623046875,
+        -0.0164794921875,
+        0.0152587890625,
+        0.034912109375,
+        0.0111083984375,
+        -0.0732421875,
+        -0.017822265625,
+        -0.02783203125,
+        -0.024658203125,
+        -0.0126953125,
+        0.00433349609375,
+        -0.0225830078125,
+        -0.0294189453125,
+        -0.006561279296875,
+        0.027587890625,
+        0.0286865234375,
+        0.0164794921875,
+        -0.048583984375,
+        -0.061279296875,
+        0.006927490234375,
+        -0.0225830078125,
+        0.01434326171875,
+        0.00130462646484375,
+        -0.07080078125,
+        -0.006011962890625,
+        -0.0228271484375,
+        0.01300048828125,
+        0.00225830078125,
+        -0.0052490234375,
+        -0.0218505859375,
+        -0.0025177001953125,
+        0.05078125,
+        -0.0283203125,
+        -0.033203125,
+        -0.0279541015625,
+        0.01025390625,
+        -0.011962890625,
+        0.015625,
+        -0.0021514892578125,
+        0.013671875,
+        0.0634765625,
+        -0.0014190673828125,
+        0.006256103515625,
+        0.000865936279296875,
+        0.03662109375,
+        -0.024169921875,
+        0.030517578125,
+        0.035888671875,
+        0.00396728515625,
+        -0.035400390625,
+        0.0311279296875,
+        -0.015869140625,
+        -0.00531005859375,
+        0.0235595703125,
+        0.003143310546875,
+        -0.02099609375,
+        -0.07177734375,
+        -0.035888671875,
+        -0.03125,
+        0.021240234375,
+        -0.04833984375,
+        -0.0299072265625,
+        -0.10791015625,
+        0.023681640625,
+        0.0291748046875,
+        0.003936767578125,
+        -0.0255126953125,
+        0.018310546875,
+        0.005767822265625,
+        0.01422119140625,
+        0.00787353515625,
+        -0.0030059814453125,
+        0.053466796875,
+        0.02734375,
+        0.024658203125,
+        -0.0081787109375,
+        0.0419921875,
+        -0.0240478515625,
+        -0.0208740234375,
+        0.004058837890625,
+        -0.03369140625,
+        0.0439453125,
+        -0.0625,
+        0.003082275390625,
+        0.01007080078125,
+        -0.047119140625,
+        -0.0224609375,
+        0.0181884765625,
+        0.0196533203125,
+        -0.004608154296875,
+        -0.0458984375,
+        0.04736328125,
+        -0.01513671875,
+        -0.08349609375,
+        -0.0576171875,
+        -0.0263671875,
+        -0.0341796875,
+        -0.017578125,
+        0.0145263671875,
+        0.06884765625,
+        0.0291748046875,
+        -0.0164794921875,
+        0.0859375,
+        -0.02685546875,
+        0.003021240234375,
+        -0.0181884765625,
+        0.041015625,
+        0.018310546875,
+        -0.04638671875,
+        -0.08056640625,
+        -0.03759765625,
+        0.0086669921875,
+        -0.0244140625,
+        0.01385498046875,
+        -0.050048828125,
+        -0.037841796875,
+        -0.014404296875,
+        0.0196533203125,
+        0.048095703125,
+        -0.05029296875,
+        0.000946044921875,
+        -0.003875732421875,
+        0.0078125,
+        -0.00726318359375,
+        -0.01275634765625,
+        0.00193023681640625,
+        -0.01556396484375,
+        -0.03857421875,
+        -0.024169921875,
+        -0.009765625,
+        -0.0208740234375,
+        -0.01141357421875,
+        -0.043701171875,
+        -0.005096435546875,
+        -0.045654296875,
+        0.064453125,
+        0.038818359375,
+        0.0004215240478515625,
+        0.0274658203125,
+        0.00299072265625,
+        -0.003265380859375,
+        -0.00811767578125,
+        -0.034912109375,
+        -0.023681640625,
+        -0.0238037109375,
+        -0.0015106201171875,
+        -0.0225830078125,
+        0.005706787109375,
+        0.040283203125,
+        0.047119140625,
+        0.00872802734375,
+        -0.00933837890625,
+        -0.0546875,
+        -0.007476806640625,
+        -0.02099609375,
+        0.056396484375,
+        0.0189208984375,
+        0.0184326171875,
+        -0.0400390625,
+        -0.0142822265625,
+        -0.0703125,
+        -0.035400390625,
+        -0.0086669921875,
+        -0.0517578125,
+        -0.0289306640625,
+        0.04736328125,
+        0.0028533935546875,
+        0.0439453125,
+        0.0301513671875,
+        0.019287109375,
+        -0.0185546875,
+        -0.0185546875,
+        -0.033935546875,
+        0.0159912109375,
+        0.01434326171875,
+        -0.0128173828125,
+        -0.0225830078125,
+        0.056884765625,
+        0.0556640625,
+        -0.03466796875,
+        0.0135498046875,
+        0.0137939453125,
+        0.0732421875,
+        -0.01116943359375,
+        -0.0128173828125,
+        -0.0004100799560546875,
+        0.01434326171875,
+        0.0299072265625,
+        -0.01446533203125,
+        -0.050048828125,
+        -0.036376953125,
+        -0.00775146484375,
+        0.00439453125,
+        0.00811767578125,
+        0.0147705078125,
+        0.01019287109375,
+        0.0019683837890625,
+        -0.00830078125,
+        -0.007659912109375,
+        0.029541015625,
+        -0.003509521484375,
+        0.043701171875,
+        -0.007781982421875,
+        0.0211181640625,
+        -0.0208740234375,
+        0.039794921875,
+        -0.03759765625,
+        0.0045166015625,
+        0.050048828125,
+        0.0196533203125,
+        0.043701171875,
+        0.00848388671875,
+        -0.043212890625,
+        -0.049560546875,
+        -0.062255859375,
+        0.0272216796875,
+        0.03662109375,
+        -0.034912109375,
+        -0.01336669921875,
+        0.05419921875,
+        -0.042236328125,
+        0.000705718994140625,
+        0.003753662109375,
+        0.0225830078125,
+        0.021240234375,
+        -0.0181884765625,
+        0.0257568359375,
+        0.0238037109375,
+        0.0034332275390625,
+        0.045166015625,
+        0.021728515625,
+        -0.0037384033203125,
+        -0.000598907470703125,
+        0.017578125,
+        -0.012939453125,
+        0.040771484375,
+        -0.05419921875,
+        -0.015380859375,
+        -0.040771484375,
+        -0.004974365234375,
+        -0.06689453125,
+        0.0419921875,
+        -0.00043487548828125,
+        0.042724609375,
+        0.01361083984375,
+        -0.013671875,
+        -0.048095703125,
+        -0.00787353515625,
+        -0.03076171875,
+        0.05078125,
+        0.0269775390625,
+        0.0028076171875,
+        -0.0233154296875,
+        -0.0023956298828125,
+        -0.02294921875,
+        -0.0517578125,
+        0.04541015625,
+        0.0035247802734375,
+        -0.004302978515625,
+        0.019775390625,
+        0.002777099609375,
+        -0.04150390625,
+        0.0150146484375,
+        0.0166015625,
+        0.01104736328125,
+        0.0252685546875,
+        0.02587890625,
+        -0.0079345703125,
+        -0.00347900390625,
+        -0.01171875,
+        -0.06298828125,
+        -0.023193359375,
+        0.0233154296875,
+        -0.0311279296875,
+        0.016845703125,
+        -0.006561279296875,
+        0.0257568359375,
+        0.048583984375,
+        -0.00567626953125,
+        -0.049072265625,
+        0.00119781494140625,
+        0.01416015625,
+        -0.0111083984375,
+        -0.01556396484375,
+        -0.022705078125,
+        -0.0184326171875,
+        -0.044189453125,
+        0.00469970703125,
+        -0.0281982421875,
+        0.031494140625,
+        0.00970458984375,
+        -0.00604248046875,
+        -0.00023937225341796875,
+        0.00732421875,
+        -0.032958984375,
+        -0.0361328125,
+        -0.00909423828125,
+        0.03857421875,
+        -0.06201171875,
+        -0.0283203125,
+        0.0791015625,
+        -0.0108642578125,
+        -0.049072265625,
+        0.01068115234375,
+        -0.049072265625,
+        -0.0380859375,
+        -0.048583984375,
+        -0.026123046875,
+        -0.00872802734375,
+        0.0021209716796875,
+        0.00140380859375,
+        -0.0260009765625,
+        0.0050048828125,
+        0.010986328125,
+        -0.0028228759765625,
+        0.0390625,
+        -0.0205078125,
+        -0.00543212890625,
+        -0.0113525390625,
+        0.045166015625,
+        0.00762939453125,
+        -0.029541015625,
+        -0.0106201171875,
+        -0.021484375,
+        -0.000362396240234375,
+        -0.025146484375,
+        -0.0419921875,
+        -0.04736328125,
+        -0.0186767578125,
+        -0.0029144287109375,
+        -0.04052734375,
+        -0.02734375,
+        -0.009521484375,
+        0.0189208984375,
+        0.033935546875,
+        -0.031982421875,
+        -0.044189453125,
+        -0.036376953125,
+        -0.0035400390625,
+        -0.0191650390625,
+        0.0184326171875,
+        -0.0133056640625,
+        -0.0240478515625,
+        -0.05712890625,
+        -0.005157470703125,
+        0.0208740234375,
+        0.0172119140625,
+        -0.0034332275390625,
+        0.068359375,
+        -0.0191650390625,
+        0.004425048828125,
+        0.04150390625,
+        -0.06689453125,
+        -0.0224609375,
+        -0.002899169921875,
+        0.0167236328125,
+        -0.032958984375,
+        0.037353515625,
+        -0.0184326171875,
+        -0.053466796875,
+        -0.0125732421875,
+        -0.04296875,
+        -0.003143310546875,
+        -0.05810546875,
+        0.068359375,
+        -0.04150390625,
+        -0.01275634765625,
+        -0.017333984375,
+        -0.06787109375,
+        -0.03466796875,
+        0.01806640625,
+        -0.00408935546875,
+        0.0294189453125,
+        -0.0498046875,
+        0.038330078125,
+        -0.0615234375,
+        0.072265625,
+        0.0267333984375,
+        -0.055908203125,
+        0.0284423828125,
+        -0.0159912109375,
+        -0.016845703125,
+        0.051513671875,
+        -0.002105712890625,
+        0.0023193359375,
+        -0.00592041015625,
+        -0.00012874603271484375,
+        0.0247802734375,
+        -0.024169921875,
+        -0.031982421875,
+        -0.0020294189453125,
+        -0.06787109375,
+        -0.0128173828125,
+        0.0057373046875,
+        0.034912109375,
+        -0.01416015625,
+        0.004638671875,
+        0.0032806396484375,
+        -0.022705078125,
+        -0.015625,
+        0.03564453125,
+        -0.0272216796875,
+        -0.042724609375,
+        -0.03271484375,
+        0.035400390625,
+        0.0419921875,
+        0.00787353515625,
+        0.0281982421875,
+        -0.0037841796875,
+        -0.01177978515625,
+        -0.03857421875,
+        0.056884765625,
+        -0.0189208984375,
+        0.061767578125,
+        -0.036865234375,
+        0.04638671875,
+        0.060302734375,
+        -0.0537109375,
+        0.0439453125,
+        0.00799560546875,
+        -0.0196533203125,
+        0.0010528564453125,
+        0.0036468505859375,
+        -0.021728515625,
+        0.0032806396484375,
+        -0.006256103515625,
+        0.017822265625,
+        -0.045166015625,
+        -0.0380859375,
+        0.0140380859375,
+        0.016357421875,
+        -0.109375,
+        -0.05859375,
+        0.047607421875,
+        0.01031494140625,
+        -0.01348876953125,
+        0.03466796875,
+        -0.01177978515625,
+        -0.013916015625,
+        -0.0205078125,
+        -0.0439453125,
+        -0.01214599609375,
+        0.035400390625,
+        -0.0184326171875,
+        -0.017822265625,
+        0.0361328125,
+        -0.03662109375,
+        0.0257568359375,
+        0.0022430419921875,
+        -0.03125,
+        -0.0267333984375,
+        -0.03271484375,
+        -0.0260009765625,
+        0.0216064453125,
+        0.04443359375,
+        -0.007293701171875,
+        -0.0177001953125,
+        -0.00286865234375,
+        -0.0017242431640625,
+        -0.0927734375,
+        -0.0164794921875,
+        0.029052734375,
+        0.0242919921875,
+        0.0040283203125,
+        0.012939453125,
+        0.03857421875,
+        0.020263671875,
+        -0.041015625,
+        -0.0169677734375,
+        -0.0301513671875,
+        0.043212890625,
+        0.045654296875,
+        0.01708984375,
+        0.036376953125,
+        0.0125732421875,
+        -0.07177734375,
+        0.006011962890625,
+        -0.01239013671875,
+        -0.0029296875,
+        0.035888671875,
+        -0.03173828125,
+        0.028564453125,
+        0.0308837890625,
+        -0.0517578125,
+        0.021728515625,
+        -0.0179443359375,
+        0.044189453125,
+        0.02783203125,
+        -0.0007476806640625,
+        0.0026397705078125,
+        0.02587890625,
+        0.0625,
+        0.06640625,
+        0.0113525390625,
+        0.027099609375,
+        0.00119781494140625,
+        -0.021484375,
+        0.0296630859375,
+        -0.0106201171875,
+        -0.023193359375,
+        0.0322265625,
+        0.03515625,
+        0.00083160400390625,
+        -0.0238037109375,
+        0.04443359375,
+        0.013671875,
+        0.011474609375,
+        -0.0205078125,
+        -0.0191650390625,
+        0.04443359375,
+        -0.0225830078125,
+        -0.017822265625,
+        -0.0341796875,
+        0.06494140625,
+        0.0294189453125,
+        -0.040771484375,
+        -0.0235595703125,
+        0.043701171875,
+        0.01318359375,
+        -0.0277099609375,
+        0.01055908203125,
+        -0.0081787109375,
+        -0.00714111328125,
+        0.030029296875,
+        -0.032470703125,
+        -0.0030364990234375,
+        0.01031494140625,
+        0.0211181640625,
+        -0.095703125,
+        -0.0003795623779296875,
+        -0.01611328125,
+        0.0205078125,
+        0.004302978515625,
+        0.00457763671875,
+        0.0281982421875,
+        -0.03955078125,
+        0.03369140625,
+        -0.011962890625,
+        -0.01348876953125,
+        0.0081787109375,
+        0.053955078125,
+        -0.02197265625,
+        -0.08935546875,
+        -0.0205078125,
+        0.0269775390625,
+        -8.153915405273438e-05,
+        -0.0296630859375,
+        0.034912109375,
+        -0.03369140625,
+        -0.001007080078125,
+        -0.045166015625,
+        -0.0093994140625,
+        0.020263671875,
+        0.0291748046875,
+        -0.026611328125,
+        -0.002197265625,
+        -0.030517578125,
+        0.0244140625,
+        0.0166015625,
+        0.0272216796875,
+        -0.001312255859375,
+        -0.034912109375,
+        0.035400390625,
+        0.0257568359375,
+        0.005279541015625,
+        0.029052734375,
+        -0.0196533203125,
+        -0.0166015625,
+        -0.0002613067626953125,
+        -0.000545501708984375,
+        0.0849609375,
+        -0.006103515625,
+        0.0390625,
+        -0.0296630859375,
+        0.041259765625,
+        0.025634765625,
+        0.01513671875,
+        -0.00555419921875,
+        0.01348876953125,
+        0.035400390625,
+        0.01409912109375,
+        -0.01806640625,
+        -0.0302734375,
+        -0.060302734375,
+        -0.016845703125,
+        -0.016845703125,
+        0.0189208984375,
+        -0.0311279296875,
+        -0.0537109375,
+        -0.0235595703125,
+        0.0269775390625,
+        -0.0010223388671875,
+        0.0299072265625,
+        0.00140380859375,
+        0.004974365234375,
+        0.00982666015625,
+        0.0028839111328125,
+        -0.0135498046875,
+        0.0203857421875,
+        -0.0235595703125,
+        -0.0283203125,
+        0.0018157958984375,
+        0.01348876953125,
+        -0.0252685546875,
+        0.0186767578125,
+        0.04052734375,
+        -0.01324462890625,
+        0.006866455078125,
+        0.022705078125,
+        0.0255126953125,
+        0.012451171875,
+        -0.0189208984375,
+        -0.007476806640625,
+        0.004425048828125,
+        0.047607421875,
+        0.0140380859375,
+        -0.06689453125,
+        0.008056640625,
+        -0.0201416015625,
+        -0.034423828125,
+        0.023193359375,
+        0.0693359375,
+        0.03125,
+        0.0245361328125,
+        -0.029052734375,
+        0.0252685546875,
+        -0.04150390625,
+        -0.007171630859375,
+        -0.0400390625,
+        0.0166015625,
+        -0.025146484375,
+        -0.0162353515625,
+        -0.019287109375,
+        -0.0223388671875,
+        -0.0089111328125,
+        0.02685546875,
+        -0.0634765625,
+        0.050537109375,
+        0.023193359375,
+        0.04931640625,
+        0.0111083984375,
+        0.01275634765625,
+        0.0380859375,
+        0.05419921875,
+        -0.05859375,
+        -0.0208740234375,
+        -0.046142578125,
+        0.01385498046875,
+        0.0081787109375,
+        0.0240478515625,
+        0.0081787109375,
+        0.04443359375,
+        -0.04736328125,
+        0.021240234375,
+        -0.0084228515625,
+        -0.005767822265625,
+        0.0140380859375,
+        -0.02587890625,
+        0.0014190673828125,
+        -0.0179443359375,
+        -0.0267333984375,
+        -0.0322265625,
+        0.036376953125,
+        -0.049560546875,
+        -0.005340576171875,
+        0.021240234375,
+        0.004913330078125,
+        0.02490234375,
+        0.007293701171875,
+        -0.0517578125,
+        0.00799560546875,
+        -0.040771484375,
+        -0.03857421875,
+        -0.040283203125,
+        -0.007568359375,
+        -0.0250244140625,
+        -0.0230712890625,
+        0.042724609375,
+        0.0172119140625,
+        -0.0185546875,
+        -0.01446533203125,
+        0.0296630859375,
+        0.02099609375,
+        0.030029296875,
+        0.03515625,
+        -0.0277099609375,
+        -0.05029296875,
+        0.031494140625,
+        -0.00262451171875,
+        -0.02001953125,
+        0.033447265625,
+        0.06103515625,
+        -0.0179443359375,
+        -0.03564453125,
+        -0.0194091796875,
+        -0.062255859375,
+        0.0037994384765625,
+        0.038330078125,
+        0.0712890625,
+        -0.0380859375,
+        0.00051116943359375,
+        0.033203125,
+        0.025634765625,
+        -0.02294921875,
+        0.0247802734375,
+        0.033935546875,
+        0.03955078125,
+        -0.01397705078125,
+        -0.006103515625,
+        -0.062255859375,
+        -0.0322265625,
+        -0.004119873046875,
+        -0.017822265625,
+        0.017333984375,
+        0.04345703125,
+        -0.002471923828125,
+        0.0277099609375,
+        -0.0162353515625,
+        0.0751953125,
+        -0.005828857421875,
+        -0.017578125,
+        -0.0220947265625,
+        -0.0439453125,
+        -0.022705078125,
+        -0.028076171875,
+        -0.0164794921875,
+        0.0260009765625,
+        -0.014892578125,
+        -0.01806640625,
+        -0.01141357421875,
+        -0.04248046875,
+        -0.0693359375,
+        0.01141357421875,
+        0.0211181640625,
+        0.007415771484375,
+        -0.03466796875,
+        0.024658203125,
+        0.016357421875,
+        0.04443359375,
+        0.00830078125,
+        -0.033447265625,
+        0.0012359619140625,
+        -0.036865234375,
+        0.0286865234375,
+        -0.04150390625,
+        -0.0308837890625,
+        0.059326171875,
+        -0.0213623046875,
+        0.0140380859375,
+        0.060302734375,
+        0.0101318359375,
+        0.052490234375,
+        0.0242919921875,
+        -0.0213623046875,
+        0.03857421875,
+        -0.000690460205078125,
+        0.048583984375,
+        -0.01300048828125,
+        0.006439208984375,
+        0.005950927734375,
+        -0.06884765625,
+        -0.004364013671875,
+        0.0302734375,
+        0.021728515625,
+        0.029541015625,
+        0.0196533203125,
+        -0.0048828125,
+        -0.0172119140625,
+        0.0009002685546875,
+        -0.0419921875,
+        -0.0185546875,
+        0.06396484375,
+        -0.0028839111328125,
+        0.0272216796875,
+        0.0247802734375,
+        -0.018310546875,
+        0.04052734375,
+        0.06494140625,
+        0.0233154296875,
+        -0.0001506805419921875,
+        -0.0250244140625,
+        -0.06103515625,
+        0.00286865234375,
+        -0.00927734375,
+        -0.01025390625,
+        -0.03466796875,
+        -0.00116729736328125,
+        0.029052734375,
+        0.0150146484375,
+        0.0130615234375,
+        0.068359375,
+        0.054931640625,
+        0.037109375,
+        0.025634765625,
+        -0.02587890625,
+        0.0458984375,
+        0.06591796875,
+        0.01239013671875,
+        -0.0262451171875,
+        0.10693359375,
+        -0.07421875,
+        -0.0174560546875,
+        -0.00604248046875,
+        -0.017578125,
+        0.06103515625,
+        0.0322265625,
+        -0.040771484375,
+        -0.0026397705078125,
+        0.0037841796875,
+        -0.05859375,
+        -0.03662109375,
+        0.0029449462890625,
+        -0.0245361328125,
+        0.0179443359375,
+        0.0220947265625,
+        0.00726318359375,
+        -0.01458740234375,
+        0.0054931640625,
+        0.036376953125,
+        0.02099609375,
+        0.0162353515625,
+        -0.0250244140625,
+        0.109375,
+        -0.024658203125,
+        -0.0206298828125,
+        -0.0269775390625,
+        -0.01043701171875,
+        -0.00994873046875,
+        -0.007720947265625,
+        -0.0002593994140625,
+        -0.01385498046875,
+        0.01153564453125,
+        0.0250244140625,
+        -0.017333984375,
+        -0.034912109375,
+        -0.004913330078125,
+        -0.0223388671875,
+        0.053955078125,
+        0.033447265625,
+        -0.01123046875,
+        -0.0213623046875,
+        0.02880859375,
+        -0.0059814453125,
+        0.00909423828125,
+        0.0021820068359375,
+        -0.050048828125,
+        0.044677734375,
+        -0.025390625,
+        -0.032958984375,
+        -0.033447265625,
+        -0.0250244140625,
+        -0.047607421875,
+        -0.02197265625,
+        -0.017333984375,
+        -0.00897216796875,
+        -0.037353515625,
+        -0.047607421875,
+        -0.006866455078125,
+        0.0145263671875,
+        0.0245361328125,
+        0.0262451171875,
+        0.01953125,
+        0.036376953125,
+        0.0859375,
+        -0.01177978515625,
+        -0.00994873046875,
+        -0.047119140625,
+        0.0166015625,
+        -0.01025390625,
+        0.0093994140625,
+        -0.0274658203125,
+        -0.0220947265625,
+        -0.03369140625,
+        -0.00518798828125,
+        -0.03466796875,
+        0.00179290771484375,
+        0.03173828125,
+        -0.0032958984375,
+        0.036376953125,
+        0.0927734375,
+        -0.01531982421875,
+        -0.037109375,
+        -0.0380859375,
+        -0.0147705078125,
+        0.026611328125,
+        -0.01165771484375,
+        -0.0322265625,
+        0.031005859375,
+        -0.0147705078125,
+        0.00885009765625,
+        0.0262451171875,
+        -0.01239013671875,
+        0.01226806640625,
+        -0.0179443359375,
+        0.030029296875,
+        -0.0234375,
+        0.0028076171875,
+        -0.00665283203125,
+        -0.0230712890625,
+        -0.0029296875,
+        -0.02783203125,
+        -0.01190185546875,
+        0.00299072265625,
+        -0.031982421875,
+        -0.021728515625,
+        0.0262451171875,
+        0.04541015625,
+        0.00189208984375,
+        0.00811767578125,
+        -0.030029296875,
+        -0.0211181640625,
+        0.05615234375,
+        0.00994873046875,
+        -0.0157470703125,
+        0.03369140625,
+        0.006683349609375,
+        0.000865936279296875,
+        -0.0059814453125,
+        -0.007476806640625,
+        -0.0238037109375,
+        0.0458984375,
+        -0.004119873046875,
+        0.0230712890625,
+        0.00732421875,
+        0.0225830078125,
+        0.0294189453125,
+        -0.0302734375,
+        -0.023681640625,
+        0.026123046875,
+        0.05029296875,
+        0.056640625,
+        0.00860595703125,
+        0.01104736328125,
+        -0.01129150390625,
+        -0.00092315673828125,
+        0.007293701171875,
+        0.040771484375,
+        0.002655029296875,
+        0.0174560546875,
+        -0.0162353515625,
+        0.045166015625,
+        -0.026123046875,
+        0.0022125244140625,
+        0.02685546875,
+        0.03173828125,
+        0.00830078125,
+        -0.0556640625,
+        -0.037109375,
+        0.0693359375,
+        0.0291748046875,
+        0.052490234375,
+        0.038818359375,
+        0.0152587890625,
+        -0.03369140625,
+        -0.0218505859375,
+        0.0157470703125,
+        -0.0260009765625,
+        0.005706787109375,
+        0.005462646484375,
+        0.00494384765625,
+        0.00885009765625,
+        0.002044677734375,
+        0.057861328125,
+        0.029296875,
+        -0.0311279296875,
+        -0.03662109375,
+        -0.01416015625,
+        0.007293701171875,
+        0.018798828125,
+        -0.043701171875,
+        0.011962890625,
+        0.0296630859375,
+        0.00299072265625,
+        -0.023681640625,
+        -0.04443359375,
+        0.0233154296875,
+        -0.031005859375,
+        0.0181884765625,
+        0.05517578125,
+        -0.0010528564453125,
+        -0.00075531005859375,
+        0.0157470703125,
+        0.015869140625,
+        -0.0419921875,
+        0.00775146484375,
+        -0.0159912109375,
+        0.0186767578125,
+        -0.03857421875,
+        0.00115966796875,
+        -0.01336669921875,
+        0.00933837890625,
+        -0.01080322265625,
+        -0.0556640625,
+        0.00433349609375,
+        -0.0147705078125,
+        0.03466796875,
+        -0.0308837890625,
+        -0.00162506103515625,
+        0.050048828125,
+        -0.04150390625,
+        -0.0198974609375,
+        -0.0155029296875,
+        0.0267333984375,
+        0.034423828125,
+        0.03466796875,
+        -0.037841796875,
+        0.034912109375,
+        0.0017547607421875,
+        0.0260009765625,
+        -0.0174560546875,
+        -0.046630859375,
+        -0.0159912109375,
+        -0.0238037109375,
+        0.04150390625,
+        -0.03759765625,
+        0.0093994140625,
+        0.0196533203125,
+        -0.019287109375,
+        0.01214599609375,
+        0.01318359375,
+        -0.0203857421875,
+        -0.01318359375,
+        -0.01904296875,
+        0.0235595703125,
+        0.0101318359375,
+        0.003326416015625,
+        -0.04345703125,
+        -0.003265380859375,
+        0.050537109375,
+        -0.021240234375,
+        0.0281982421875,
+        -0.004302978515625,
+        0.0595703125,
+        -0.0062255859375,
+        0.0145263671875,
+        0.01214599609375,
+        0.00250244140625,
+        -0.00909423828125,
+        -0.01519775390625,
+        -0.018310546875,
+        0.00946044921875,
+        -0.064453125,
+        0.052490234375,
+        0.037353515625,
+        0.00823974609375,
+        -0.0074462890625,
+        -0.044189453125,
+        0.023193359375,
+        0.0400390625,
+        0.003143310546875,
+        -0.00012493133544921875,
+        -0.0230712890625,
+        -0.0169677734375,
+        -0.0032806396484375,
+        -0.0269775390625,
+        0.01495361328125,
+        0.033203125,
+        -0.0390625,
+        0.024169921875,
+        -0.05517578125,
+        0.01416015625,
+        -0.0057373046875,
+        0.052490234375,
+        -0.00439453125,
+        -0.039306640625,
+        -0.08056640625,
+        0.049072265625,
+        0.002227783203125,
+        0.02197265625,
+        -0.052978515625,
+        -0.0203857421875,
+        0.034423828125,
+        -0.0096435546875,
+        0.043212890625,
+        0.0361328125,
+        -0.03662109375,
+        0.038330078125,
+        -0.0380859375,
+        -0.040283203125,
+        0.0213623046875,
+        0.02294921875,
+        -0.00152587890625,
+        -0.04296875,
+        0.0400390625,
+        -0.01361083984375,
+        -0.00872802734375,
+        -0.03125,
+        -0.007476806640625,
+        0.0267333984375,
+        -0.000583648681640625,
+        -0.06201171875,
+        -0.048828125,
+        0.041015625,
+        -0.000545501708984375,
+        0.041015625,
+        0.052001953125,
+        0.019287109375,
+        -0.014892578125,
+        0.01434326171875,
+        0.0120849609375,
+        0.0059814453125,
+        -0.0186767578125,
+        0.01483154296875,
+        -0.02978515625,
+        -0.024658203125,
+        -0.0322265625,
+        0.056396484375,
+        0.061279296875,
+        -0.02099609375,
+        -0.0172119140625,
+        0.0279541015625,
+        0.02294921875,
+        -0.02099609375,
+        -0.04541015625,
+        -0.00897216796875,
+        -0.032470703125,
+        0.040283203125,
+        -0.040283203125,
+        -0.040771484375,
+        -0.06787109375
+      ]
+    ]
+  ],
+  "hd_transform_order": "sub_glb",
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "image_size": 448,
+  "img_processor": {
+    "_attn_implementation_autoset": true,
+    "_flash_attn_2_enabled": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "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": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 448,
+    "intermediate_size": 4304,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "siglip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.51.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "interpolate_factor": 1,
+  "lm_head_bias": false,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "phi4mm",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 32,
+  "num_img_tokens": 256,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 199999,
+  "partial_rotary_factor": 0.75,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "short_factor": [
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "speech_lora": {
+    "dp": 0.01,
+    "layer": "((layers.*self_attn\\.(qkv|o)_proj)|(layers.*mlp\\.(gate_up|down)_proj))",
+    "lora_alpha": 640,
+    "r": 320
+  },
+  "sub_GN": [
+    [
+      [
+        [
+          0.01287841796875,
+          0.01202392578125,
+          -0.0006866455078125,
+          -0.004180908203125,
+          -3.743171691894531e-05,
+          -0.000934600830078125,
+          0.001434326171875,
+          0.007476806640625,
+          -0.0035400390625,
+          -0.0196533203125,
+          0.00775146484375,
+          0.00098419189453125,
+          0.00921630859375,
+          3.218650817871094e-05,
+          0.009765625,
+          -0.0120849609375,
+          -0.004241943359375,
+          0.00994873046875,
+          0.0013580322265625,
+          0.0012054443359375,
+          0.0047607421875,
+          -0.00185394287109375,
+          -0.0242919921875,
+          0.01214599609375,
+          -0.0101318359375,
+          -0.00070953369140625,
+          -0.005126953125,
+          -0.004425048828125,
+          -0.01251220703125,
+          0.004119873046875,
+          -0.00274658203125,
+          -0.01055908203125,
+          0.00494384765625,
+          -0.0028228759765625,
+          0.0024261474609375,
+          0.0064697265625,
+          0.000865936279296875,
+          -0.00103759765625,
+          -0.0025787353515625,
+          0.0166015625,
+          -0.000675201416015625,
+          0.01177978515625,
+          -0.00018024444580078125,
+          0.00238037109375,
+          -0.003326416015625,
+          0.00153350830078125,
+          -0.00086212158203125,
+          -0.00628662109375,
+          -6.079673767089844e-05,
+          0.005828857421875,
+          0.001495361328125,
+          -0.01275634765625,
+          -0.00909423828125,
+          0.00592041015625,
+          4.863739013671875e-05,
+          0.0067138671875,
+          -0.003631591796875,
+          0.0024871826171875,
+          -8.106231689453125e-05,
+          -0.00148773193359375,
+          -1.2993812561035156e-05,
+          0.00982666015625,
+          0.004669189453125,
+          -0.003570556640625,
+          0.01092529296875,
+          0.0174560546875,
+          -0.005645751953125,
+          0.01263427734375,
+          0.00909423828125,
+          -0.00494384765625,
+          0.00604248046875,
+          -0.0164794921875,
+          -0.0016326904296875,
+          -0.00112152099609375,
+          0.00177764892578125,
+          -0.00139617919921875,
+          -0.00653076171875,
+          0.00982666015625,
+          0.000370025634765625,
+          -0.0159912109375,
+          0.00171661376953125,
+          0.0164794921875,
+          -0.0074462890625,
+          -0.004638671875,
+          -0.01007080078125,
+          -0.004913330078125,
+          0.0177001953125,
+          -0.00689697265625,
+          0.0059814453125,
+          0.014892578125,
+          -0.00927734375,
+          0.025146484375,
+          0.0042724609375,
+          -0.00060272216796875,
+          0.0189208984375,
+          0.007232666015625,
+          -0.002349853515625,
+          0.01483154296875,
+          -0.005279541015625,
+          -0.00933837890625,
+          -0.000530242919921875,
+          -0.00811767578125,
+          0.00848388671875,
+          0.00225830078125,
+          -0.0026702880859375,
+          -0.016357421875,
+          0.0034027099609375,
+          -0.006317138671875,
+          -0.00830078125,
+          -0.007476806640625,
+          0.016357421875,
+          0.00408935546875,
+          -0.0016632080078125,
+          -0.00872802734375,
+          -0.00787353515625,
+          -0.0021820068359375,
+          0.00185394287109375,
+          -0.002685546875,
+          -0.013427734375,
+          -0.006744384765625,
+          4.267692565917969e-05,
+          0.00372314453125,
+          -0.005340576171875,
+          0.0010223388671875,
+          -0.0078125,
+          -0.0021209716796875,
+          0.00994873046875,
+          0.00616455078125,
+          0.0277099609375,
+          -0.0096435546875,
+          -0.01300048828125,
+          -0.0167236328125,
+          -0.01220703125,
+          -0.01214599609375,
+          -0.0016326904296875,
+          -0.002685546875,
+          0.0016632080078125,
+          -0.0177001953125,
+          -0.01080322265625,
+          -0.009521484375,
+          0.009765625,
+          0.0107421875,
+          0.007171630859375,
+          -0.0030364990234375,
+          0.01141357421875,
+          -0.012451171875,
+          -0.004608154296875,
+          0.004669189453125,
+          -0.003265380859375,
+          -0.00970458984375,
+          -0.00860595703125,
+          -0.0103759765625,
+          0.003326416015625,
+          0.0167236328125,
+          0.0084228515625,
+          0.000736236572265625,
+          -0.0032806396484375,
+          0.0125732421875,
+          -0.004241943359375,
+          0.0123291015625,
+          -0.0057373046875,
+          0.0081787109375,
+          0.0029296875,
+          -0.00872802734375,
+          -0.00150299072265625,
+          0.01275634765625,
+          0.0016937255859375,
+          -0.00616455078125,
+          0.01275634765625,
+          -0.0007171630859375,
+          -0.0220947265625,
+          -0.0042724609375,
+          -0.000949859619140625,
+          0.004486083984375,
+          0.0029754638671875,
+          -0.004638671875,
+          0.0076904296875,
+          0.00070953369140625,
+          0.0029449462890625,
+          0.002227783203125,
+          -0.01544189453125,
+          -0.01080322265625,
+          -0.00057220458984375,
+          0.00021648406982421875,
+          0.019775390625,
+          -0.006317138671875,
+          -0.017333984375,
+          -0.015869140625,
+          -0.0032958984375,
+          0.0120849609375,
+          0.00518798828125,
+          0.004669189453125,
+          0.0164794921875,
+          0.004119873046875,
+          -0.0007476806640625,
+          -0.0036773681640625,
+          -0.001953125,
+          -0.006805419921875,
+          0.007537841796875,
+          0.003265380859375,
+          -0.017822265625,
+          -0.00592041015625,
+          -0.00131988525390625,
+          0.00714111328125,
+          0.0079345703125,
+          -0.0015106201171875,
+          0.004119873046875,
+          0.0027008056640625,
+          0.01531982421875,
+          -0.00537109375,
+          -0.00225830078125,
+          -0.0001583099365234375,
+          -0.005828857421875,
+          0.01336669921875,
+          -0.0069580078125,
+          0.01312255859375,
+          0.0262451171875,
+          -0.0027923583984375,
+          0.006103515625,
+          -0.0166015625,
+          0.0074462890625,
+          0.01092529296875,
+          0.005859375,
+          -0.00921630859375,
+          0.00640869140625,
+          -0.01007080078125,
+          0.002105712890625,
+          0.006072998046875,
+          -0.0093994140625,
+          0.006011962890625,
+          -0.004425048828125,
+          -0.0164794921875,
+          -0.00909423828125,
+          -0.017333984375,
+          0.00823974609375,
+          -0.007293701171875,
+          0.006744384765625,
+          -0.005340576171875,
+          -0.004241943359375,
+          0.00799560546875,
+          -0.0048828125,
+          -0.01513671875,
+          -0.011474609375,
+          -0.00897216796875,
+          0.017578125,
+          -0.006683349609375,
+          0.01025390625,
+          -0.0059814453125,
+          -8.153915405273438e-05,
+          0.00750732421875,
+          0.0020294189453125,
+          -0.0033721923828125,
+          0.00250244140625,
+          0.005523681640625,
+          -0.00150299072265625,
+          -0.00994873046875,
+          0.00110626220703125,
+          0.0084228515625,
+          -0.0098876953125,
+          -0.0245361328125,
+          -0.01495361328125,
+          -0.0078125,
+          -0.0137939453125,
+          -0.00093841552734375,
+          -0.00811767578125,
+          -0.003631591796875,
+          -0.010009765625,
+          -0.01519775390625,
+          0.00677490234375,
+          0.0140380859375,
+          -0.0064697265625,
+          -0.002349853515625,
+          0.003021240234375,
+          -0.0032501220703125,
+          -0.001434326171875,
+          -0.0120849609375,
+          0.00421142578125,
+          -0.0130615234375,
+          -0.001068115234375,
+          -0.0126953125,
+          0.0022125244140625,
+          -0.000629425048828125,
+          -0.00140380859375,
+          0.004669189453125,
+          0.0062255859375,
+          0.005584716796875,
+          0.0018463134765625,
+          0.01116943359375,
+          -0.0062255859375,
+          0.0009918212890625,
+          0.00122833251953125,
+          0.01141357421875,
+          -0.009521484375,
+          0.017578125,
+          0.006561279296875,
+          0.003875732421875,
+          -0.0107421875,
+          -0.00994873046875,
+          -0.0069580078125,
+          0.01470947265625,
+          -0.00421142578125,
+          0.006103515625,
+          0.000392913818359375,
+          0.004119873046875,
+          0.0052490234375,
+          -0.00060272216796875,
+          -0.01080322265625,
+          -0.01068115234375,
+          -0.000774383544921875,
+          -0.0172119140625,
+          -0.000835418701171875,
+          -0.0096435546875,
+          0.0022735595703125,
+          -0.001434326171875,
+          0.003692626953125,
+          -0.00119781494140625,
+          0.0026092529296875,
+          0.02490234375,
+          0.015380859375,
+          -0.0201416015625,
+          0.0238037109375,
+          -0.0103759765625,
+          -0.009033203125,
+          -0.01348876953125,
+          0.00125885009765625,
+          0.016845703125,
+          -0.0028533935546875,
+          -0.005126953125,
+          -0.0130615234375,
+          -0.00970458984375,
+          0.00933837890625,
+          0.01611328125,
+          -0.0076904296875,
+          -0.002197265625,
+          0.006988525390625,
+          -0.0223388671875,
+          0.00445556640625,
+          -0.00433349609375,
+          0.0084228515625,
+          -0.00762939453125,
+          -0.0064697265625,
+          0.0150146484375,
+          0.0150146484375,
+          -0.017333984375,
+          0.017822265625,
+          0.00177764892578125,
+          0.00921630859375,
+          -0.00927734375,
+          0.0028533935546875,
+          -2.2411346435546875e-05,
+          -0.00130462646484375,
+          -0.00433349609375,
+          -0.0013580322265625,
+          0.01202392578125,
+          -0.0029754638671875,
+          -0.000385284423828125,
+          -0.004608154296875,
+          -0.0037841796875,
+          0.002166748046875,
+          0.01068115234375,
+          -0.00506591796875,
+          0.001617431640625,
+          -0.0107421875,
+          -7.724761962890625e-05,
+          -0.005523681640625,
+          0.012451171875,
+          -0.00341796875,
+          0.00286865234375,
+          0.0244140625,
+          0.0032196044921875,
+          0.0048828125,
+          0.0177001953125,
+          -0.006072998046875,
+          0.0087890625,
+          0.00017833709716796875,
+          -0.00799560546875,
+          -0.0250244140625,
+          0.003326416015625,
+          0.0017242431640625,
+          0.004791259765625,
+          -0.0159912109375,
+          -0.00177764892578125,
+          0.019775390625,
+          -0.0086669921875,
+          0.01422119140625,
+          -0.005950927734375,
+          0.005035400390625,
+          -0.011474609375,
+          0.00238037109375,
+          -0.004547119140625,
+          0.01177978515625,
+          0.0115966796875,
+          0.0030517578125,
+          -8.7738037109375e-05,
+          -0.00335693359375,
+          0.00592041015625,
+          0.009033203125,
+          0.00139617919921875,
+          -0.0185546875,
+          -0.004547119140625,
+          0.00543212890625,
+          0.02001953125,
+          -0.01019287109375,
+          -0.01275634765625,
+          0.005950927734375,
+          0.00921630859375,
+          0.00131988525390625,
+          2.2530555725097656e-05,
+          -0.00604248046875,
+          0.00885009765625,
+          -0.000335693359375,
+          -0.00848388671875,
+          -0.0072021484375,
+          0.0037841796875,
+          0.00177764892578125,
+          -0.0113525390625,
+          -0.00909423828125,
+          0.004669189453125,
+          -0.01153564453125,
+          0.00390625,
+          0.01116943359375,
+          -0.002288818359375,
+          -0.005615234375,
+          -0.00051116943359375,
+          0.0029144287109375,
+          0.0159912109375,
+          -0.017578125,
+          -0.01416015625,
+          0.0017547607421875,
+          0.00933837890625,
+          0.000835418701171875,
+          0.0064697265625,
+          -0.01080322265625,
+          0.0172119140625,
+          -0.007659912109375,
+          0.00159454345703125,
+          0.006500244140625,
+          -0.00750732421875,
+          0.002532958984375,
+          -0.00909423828125,
+          0.006744384765625,
+          -0.0133056640625,
+          0.002288818359375,
+          -0.00101470947265625,
+          0.003753662109375,
+          -0.0128173828125,
+          0.0081787109375,
+          0.000247955322265625,
+          -0.004302978515625,
+          0.01300048828125,
+          -0.0019989013671875,
+          0.01031494140625,
+          0.0015869140625,
+          0.0135498046875,
+          -0.00323486328125,
+          -0.00021648406982421875,
+          0.00927734375,
+          -0.01226806640625,
+          -0.00946044921875,
+          0.011474609375,
+          -0.01031494140625,
+          -0.006927490234375,
+          -0.0118408203125,
+          0.004913330078125,
+          0.01446533203125,
+          0.0174560546875,
+          -0.00153350830078125,
+          0.005126953125,
+          0.00113677978515625,
+          -0.000141143798828125,
+          0.01373291015625,
+          0.00738525390625,
+          -0.007415771484375,
+          -0.005615234375,
+          -0.00927734375,
+          0.012939453125,
+          0.00173187255859375,
+          -0.00043487548828125,
+          -0.012451171875,
+          0.0101318359375,
+          -0.00150299072265625,
+          -0.006591796875,
+          0.0107421875,
+          0.025634765625,
+          0.0003414154052734375,
+          -0.00017070770263671875,
+          -0.01171875,
+          0.01806640625,
+          0.006256103515625,
+          0.00982666015625,
+          -0.0030670166015625,
+          -0.0091552734375,
+          -0.0179443359375,
+          0.0020751953125,
+          0.006744384765625,
+          -0.00445556640625,
+          -0.00335693359375,
+          -0.00543212890625,
+          -0.015869140625,
+          -0.005523681640625,
+          0.0118408203125,
+          0.0011138916015625,
+          -0.00543212890625,
+          -0.00013637542724609375,
+          -0.001617431640625,
+          0.001617431640625,
+          0.004150390625,
+          0.00074005126953125,
+          -0.019287109375,
+          -0.0078125,
+          -0.016357421875,
+          -0.0146484375,
+          -0.003143310546875,
+          0.0025787353515625,
+          -0.019287109375,
+          -0.005218505859375,
+          -0.00830078125,
+          0.01080322265625,
+          -0.004180908203125,
+          -0.009765625,
+          -0.006927490234375,
+          -0.00823974609375,
+          -0.005035400390625,
+          -0.0185546875,
+          -0.019775390625,
+          0.00011396408081054688,
+          -0.0020751953125,
+          -0.00927734375,
+          -0.006622314453125,
+          0.0037078857421875,
+          -0.0027923583984375,
+          0.0017242431640625,
+          0.001983642578125,
+          -0.007080078125,
+          -0.00640869140625,
+          -0.007659912109375,
+          0.0072021484375,
+          0.002044677734375,
+          -0.01214599609375,
+          0.00171661376953125,
+          -0.0003204345703125,
+          -0.0002765655517578125,
+          0.00921630859375,
+          0.00738525390625,
+          0.00958251953125,
+          -0.000583648681640625,
+          -0.0169677734375,
+          0.000453948974609375,
+          0.006317138671875,
+          -0.0137939453125,
+          -0.018798828125,
+          0.0196533203125,
+          0.01434326171875,
+          0.0030059814453125,
+          0.006195068359375,
+          0.01025390625,
+          0.015625,
+          -0.00897216796875,
+          0.004638671875,
+          -0.03466796875,
+          -0.0008697509765625,
+          -0.000835418701171875,
+          0.0024261474609375,
+          -0.012939453125,
+          0.00848388671875,
+          -0.000820159912109375,
+          -0.00927734375,
+          -0.015625,
+          0.00567626953125,
+          -0.0016632080078125,
+          -0.0019989013671875,
+          -0.0028533935546875,
+          -0.002777099609375,
+          0.0025482177734375,
+          0.01055908203125,
+          0.00714111328125,
+          -0.01055908203125,
+          0.00162506103515625,
+          0.0098876953125,
+          -0.00421142578125,
+          0.0024261474609375,
+          0.01373291015625,
+          0.01611328125,
+          -0.0106201171875,
+          -0.0004405975341796875,
+          -0.0045166015625,
+          -0.0038909912109375,
+          0.00145721435546875,
+          0.01123046875,
+          0.0022430419921875,
+          -0.0078125,
+          0.01177978515625,
+          -0.00142669677734375,
+          -0.000701904296875,
+          -0.0009613037109375,
+          0.01556396484375,
+          0.01019287109375,
+          -0.0155029296875,
+          -0.00537109375,
+          0.01483154296875,
+          -0.01043701171875,
+          0.01165771484375,
+          -0.00799560546875,
+          -0.00390625,
+          -0.00174713134765625,
+          0.009033203125,
+          0.00372314453125,
+          -0.004852294921875,
+          -0.003082275390625,
+          0.012939453125,
+          -0.01055908203125,
+          -0.0052490234375,
+          0.0022125244140625,
+          0.001556396484375,
+          -0.010498046875,
+          0.0020599365234375,
+          0.01611328125,
+          -0.00994873046875,
+          -0.0189208984375,
+          -0.007537841796875,
+          -0.00150299072265625,
+          1.0192394256591797e-05,
+          -0.007598876953125,
+          0.0047607421875,
+          -0.0096435546875,
+          -0.0166015625,
+          0.0126953125,
+          -0.004547119140625,
+          -0.005828857421875,
+          0.0007781982421875,
+          -0.0074462890625,
+          0.000701904296875,
+          0.0018768310546875,
+          0.00396728515625,
+          0.0107421875,
+          -0.0062255859375,
+          0.0211181640625,
+          -0.0194091796875,
+          0.004058837890625,
+          -0.005096435546875,
+          0.0036773681640625,
+          0.00726318359375,
+          -0.003662109375,
+          0.00885009765625,
+          -0.008056640625,
+          0.01446533203125,
+          -0.010009765625,
+          0.002288818359375,
+          0.000629425048828125,
+          0.003814697265625,
+          7.581710815429688e-05,
+          0.001739501953125,
+          -0.0068359375,
+          0.00640869140625,
+          0.002655029296875,
+          0.0115966796875,
+          -0.0062255859375,
+          -0.0032806396484375,
+          0.01116943359375,
+          0.000690460205078125,
+          -0.0062255859375,
+          -0.01043701171875,
+          0.0003662109375,
+          0.01519775390625,
+          -0.00384521484375,
+          0.002227783203125,
+          -0.0027618408203125,
+          -0.01171875,
+          0.00286865234375,
+          -0.001495361328125,
+          0.00177764892578125,
+          -0.009033203125,
+          -0.006744384765625,
+          -0.0184326171875,
+          0.0023193359375,
+          -0.01190185546875,
+          0.006103515625,
+          0.005218505859375,
+          5.3882598876953125e-05,
+          0.0013427734375,
+          0.00360107421875,
+          -0.0031585693359375,
+          0.0068359375,
+          0.00156402587890625,
+          0.0050048828125,
+          0.02001953125,
+          -0.00323486328125,
+          -0.01165771484375,
+          -0.01275634765625,
+          0.0002269744873046875,
+          0.00104522705078125,
+          -0.0004177093505859375,
+          -0.006500244140625,
+          0.0008087158203125,
+          -0.01123046875,
+          0.00823974609375,
+          0.00738525390625,
+          -0.0019683837890625,
+          -0.005340576171875,
+          -0.01214599609375,
+          -0.0027008056640625,
+          0.0040283203125,
+          0.01220703125,
+          -0.006988525390625,
+          -0.00579833984375,
+          0.00372314453125,
+          -0.002197265625,
+          -0.007720947265625,
+          -0.005157470703125,
+          -0.003448486328125,
+          -0.011962890625,
+          0.0125732421875,
+          -0.00125885009765625,
+          0.0010223388671875,
+          0.0012054443359375,
+          -0.0150146484375,
+          -0.00127410888671875,
+          0.01007080078125,
+          0.00445556640625,
+          -0.001190185546875,
+          0.006866455078125,
+          0.0164794921875,
+          -0.018310546875,
+          -0.00408935546875,
+          -0.0001392364501953125,
+          0.00543212890625,
+          0.0020294189453125,
+          0.0003986358642578125,
+          0.010498046875,
+          -0.0189208984375,
+          -0.01263427734375,
+          -0.000972747802734375,
+          -0.00787353515625,
+          0.00811767578125,
+          -0.01263427734375,
+          -0.006500244140625,
+          -0.00689697265625,
+          0.01263427734375,
+          -0.0024566650390625,
+          0.0198974609375,
+          -0.006805419921875,
+          0.00958251953125,
+          -0.0107421875,
+          -0.0031585693359375,
+          0.021484375,
+          -0.0118408203125,
+          -0.001708984375,
+          0.00982666015625,
+          -0.0022430419921875,
+          -0.01025390625,
+          -0.00762939453125,
+          -0.0162353515625,
+          -0.00057220458984375,
+          0.00286865234375,
+          -0.0020904541015625,
+          -0.000255584716796875,
+          0.01104736328125,
+          -0.006683349609375,
+          0.0020751953125,
+          0.000362396240234375,
+          -0.0052490234375,
+          0.0011444091796875,
+          -0.021484375,
+          -0.00026702880859375,
+          0.010009765625,
+          -0.0057373046875,
+          0.0140380859375,
+          -0.00946044921875,
+          0.0072021484375,
+          0.0028076171875,
+          -0.0159912109375,
+          -0.00335693359375,
+          0.0177001953125,
+          0.0027923583984375,
+          0.005706787109375,
+          0.005584716796875,
+          0.0084228515625,
+          -0.001434326171875,
+          -0.00958251953125,
+          -0.00848388671875,
+          -0.0093994140625,
+          -0.0093994140625,
+          0.01214599609375,
+          -0.01312255859375,
+          -0.01287841796875,
+          -0.004638671875,
+          -0.002410888671875,
+          0.005828857421875,
+          -0.004669189453125,
+          -0.006927490234375,
+          0.002716064453125,
+          -0.0089111328125,
+          0.004730224609375,
+          0.0157470703125,
+          -0.00173187255859375,
+          0.00823974609375,
+          -0.00106048583984375,
+          -0.01953125,
+          0.0009918212890625,
+          0.0026397705078125,
+          0.01397705078125,
+          0.003265380859375,
+          0.001556396484375,
+          -0.00116729736328125,
+          -0.001617431640625,
+          0.009033203125,
+          -0.00823974609375,
+          0.00732421875,
+          -0.002197265625,
+          -0.01495361328125,
+          -0.019775390625,
+          0.004058837890625,
+          0.01513671875,
+          0.008056640625,
+          -0.0111083984375,
+          0.0068359375,
+          0.004669189453125,
+          0.01409912109375,
+          0.0001277923583984375,
+          -0.0036773681640625,
+          -0.00555419921875,
+          0.00408935546875,
+          -0.01531982421875,
+          0.00081634521484375,
+          0.007080078125,
+          -0.01080322265625,
+          0.00665283203125,
+          -0.005584716796875,
+          -0.00457763671875,
+          -0.0125732421875,
+          0.01141357421875,
+          -0.0108642578125,
+          0.0277099609375,
+          -0.016845703125,
+          -0.01385498046875,
+          -0.0107421875,
+          -0.0123291015625,
+          -0.01483154296875,
+          -0.0005035400390625,
+          -0.00677490234375,
+          -0.006805419921875,
+          0.0301513671875,
+          0.00982666015625,
+          -0.00194549560546875,
+          0.01519775390625,
+          0.0028076171875,
+          -0.01531982421875,
+          -0.0076904296875,
+          0.0048828125,
+          0.00726318359375,
+          -0.004119873046875,
+          -0.008056640625,
+          0.0037689208984375,
+          0.01556396484375,
+          -0.022216796875,
+          -0.0079345703125,
+          0.01446533203125,
+          0.00933837890625,
+          0.01129150390625,
+          -0.021240234375,
+          0.0038604736328125,
+          -0.00396728515625,
+          -0.001678466796875,
+          0.005706787109375,
+          -0.006683349609375,
+          -0.0009002685546875,
+          -0.00075531005859375,
+          -0.00020122528076171875,
+          -0.00127410888671875,
+          -0.016845703125,
+          0.0011138916015625,
+          0.0145263671875,
+          -0.002593994140625,
+          0.00262451171875,
+          0.0034027099609375,
+          -0.0010528564453125,
+          -0.0040283203125,
+          0.0008392333984375,
+          -0.00054168701171875,
+          0.005950927734375,
+          0.0155029296875,
+          0.0050048828125,
+          0.000873565673828125,
+          0.007476806640625,
+          -0.0206298828125,
+          0.00135040283203125,
+          0.000751495361328125,
+          0.0057373046875,
+          0.0016021728515625,
+          0.0098876953125,
+          0.0093994140625,
+          0.00408935546875,
+          -0.0174560546875,
+          -0.01495361328125,
+          0.00244140625,
+          0.00836181640625,
+          -0.00213623046875,
+          0.0004024505615234375,
+          0.00640869140625,
+          -0.001953125,
+          0.0089111328125,
+          -0.005584716796875,
+          0.006591796875,
+          0.004730224609375,
+          0.0010223388671875,
+          0.0125732421875,
+          0.007476806640625,
+          -0.00058746337890625,
+          0.004974365234375,
+          0.01531982421875,
+          0.003936767578125,
+          -0.005706787109375,
+          0.005157470703125,
+          -0.00156402587890625,
+          0.001983642578125,
+          0.0115966796875,
+          -0.0272216796875,
+          -0.01953125,
+          -0.00025177001953125,
+          -0.003173828125,
+          -0.003173828125,
+          0.00897216796875,
+          -0.01202392578125,
+          -0.002471923828125,
+          0.01556396484375,
+          0.001190185546875,
+          -0.0218505859375,
+          -2.9802322387695312e-05,
+          -0.015869140625,
+          0.0118408203125,
+          -0.004974365234375,
+          -0.00347900390625,
+          -0.003997802734375,
+          -0.0029296875,
+          -0.00390625,
+          0.0150146484375,
+          0.00457763671875,
+          -0.00020313262939453125,
+          -0.005157470703125,
+          -0.010009765625,
+          -0.0022735595703125,
+          0.006561279296875,
+          -0.0103759765625,
+          -0.01239013671875,
+          0.0045166015625,
+          -0.0030670166015625,
+          -0.00933837890625,
+          -0.00616455078125,
+          -0.00250244140625,
+          0.01031494140625,
+          0.00193023681640625,
+          -0.0035247802734375,
+          0.001251220703125,
+          0.0022735595703125,
+          -0.006378173828125,
+          -0.00787353515625,
+          -0.0263671875,
+          -0.007537841796875,
+          -0.001953125,
+          0.01177978515625,
+          -0.0037078857421875,
+          -0.01556396484375,
+          -0.00897216796875,
+          -0.0032958984375,
+          0.00860595703125,
+          -0.002288818359375,
+          -0.002105712890625,
+          -0.0042724609375,
+          -0.0205078125,
+          0.0069580078125,
+          -0.0028076171875,
+          0.004302978515625,
+          -0.0146484375,
+          0.00665283203125,
+          -0.0004367828369140625,
+          -0.01275634765625,
+          -0.001068115234375,
+          -0.007720947265625,
+          0.01544189453125,
+          0.0218505859375,
+          -0.01953125,
+          -0.00897216796875,
+          -0.0186767578125,
+          0.0081787109375,
+          -0.001495361328125,
+          0.007110595703125,
+          0.01202392578125,
+          -0.0118408203125,
+          -0.007568359375,
+          -0.007080078125,
+          -0.00848388671875,
+          -0.004669189453125,
+          0.00469970703125,
+          -0.0008392333984375,
+          0.0022125244140625,
+          0.0032958984375,
+          -0.01025390625,
+          0.006072998046875,
+          0.0030975341796875,
+          0.002349853515625,
+          0.00762939453125,
+          0.0079345703125,
+          -0.0013427734375,
+          -0.00238037109375,
+          -0.003814697265625,
+          -0.001983642578125,
+          0.0025177001953125,
+          -0.01513671875,
+          0.005645751953125,
+          -0.00013065338134765625,
+          -0.0113525390625,
+          -0.0038299560546875,
+          -0.00927734375,
+          -0.0125732421875,
+          -0.004669189453125,
+          -0.0033416748046875,
+          -0.0035552978515625,
+          0.0093994140625,
+          0.00189971923828125,
+          -9.250640869140625e-05,
+          0.000164031982421875,
+          0.000568389892578125,
+          0.00537109375,
+          -0.005523681640625,
+          0.002899169921875,
+          -0.0098876953125,
+          -0.0137939453125,
+          -0.0030059814453125,
+          -0.00701904296875,
+          -0.0084228515625,
+          -0.000823974609375,
+          0.00799560546875,
+          -0.005706787109375,
+          0.00823974609375,
+          -0.00946044921875,
+          -0.0030517578125,
+          -0.0169677734375,
+          0.006378173828125,
+          0.0024566650390625,
+          0.00775146484375,
+          0.00101470947265625,
+          -0.00848388671875,
+          -0.003265380859375,
+          -0.004608154296875,
+          -0.004364013671875,
+          0.001312255859375,
+          0.0111083984375,
+          0.001312255859375,
+          -0.0078125,
+          0.0003509521484375,
+          -0.00131988525390625,
+          -0.0024261474609375,
+          0.0047607421875,
+          -0.01129150390625,
+          0.005645751953125,
+          -0.0103759765625,
+          0.007232666015625,
+          0.000408172607421875,
+          0.006011962890625,
+          0.004547119140625,
+          0.00136566162109375,
+          -0.01361083984375,
+          -0.01055908203125,
+          -0.000904083251953125,
+          0.003509521484375,
+          0.0037689208984375,
+          -0.024658203125,
+          0.00909423828125,
+          0.0034942626953125,
+          0.0113525390625,
+          0.005859375,
+          -0.0027313232421875,
+          0.0010528564453125,
+          0.0164794921875,
+          -0.01226806640625,
+          -0.013427734375,
+          0.00023746490478515625,
+          0.01409912109375,
+          0.01123046875,
+          -0.00872802734375,
+          -0.0010528564453125,
+          0.006011962890625,
+          -0.004608154296875,
+          0.00738525390625,
+          -0.00341796875,
+          -0.00482177734375,
+          0.0024261474609375,
+          0.0089111328125,
+          0.0048828125,
+          0.007110595703125,
+          0.002899169921875,
+          -0.004302978515625,
+          0.004486083984375,
+          0.00714111328125,
+          0.0035858154296875,
+          -0.01092529296875,
+          0.0045166015625,
+          0.00148773193359375,
+          0.00118255615234375,
+          0.00439453125,
+          -0.0135498046875,
+          0.005523681640625,
+          -0.01055908203125,
+          -0.004364013671875,
+          -0.00567626953125,
+          -0.0050048828125,
+          -0.006011962890625,
+          -0.00848388671875,
+          -0.000545501708984375,
+          -0.01153564453125,
+          0.00579833984375,
+          0.0064697265625,
+          -0.004180908203125,
+          -0.00311279296875,
+          -0.000888824462890625,
+          0.0025177001953125,
+          0.0012054443359375,
+          0.0087890625,
+          -0.005401611328125,
+          0.0032806396484375,
+          -0.01190185546875,
+          -0.009033203125,
+          -0.0111083984375,
+          -0.000640869140625,
+          -0.009765625,
+          -0.0167236328125,
+          -0.0023956298828125,
+          0.00023937225341796875,
+          -0.0189208984375,
+          -0.007080078125,
+          -0.00014019012451171875,
+          -0.00958251953125,
+          -0.0076904296875,
+          -0.0027008056640625,
+          0.0047607421875,
+          0.0087890625,
+          -0.0047607421875,
+          -1.0967254638671875e-05,
+          0.010009765625,
+          0.003387451171875,
+          0.015869140625,
+          0.0096435546875,
+          0.010009765625,
+          1.1861324310302734e-05,
+          0.001678466796875,
+          -0.00055694580078125,
+          -0.00140380859375,
+          -0.0031280517578125,
+          -0.005645751953125,
+          -0.00162506103515625,
+          -0.003326416015625,
+          0.0181884765625
+        ]
+      ]
+    ]
+  ],
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "vision_lora": {
+    "dp": 0.0,
+    "layer": "layers.*((self_attn\\.(qkv_proj|o_proj))|(mlp\\.(gate_up|down)_proj))",
+    "lora_alpha": 512,
+    "r": 256
+  },
+  "vocab_size": 200064
+}

configuration_phi4mm.py

@@ -0,0 +1,235 @@
+# coding=utf-8
+# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+""" Phi-4-MM model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+
+class Phi4MMConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`Phi4MMModel`]. It is used to instantiate a Phi-4-MM
+    model according to the specified arguments, defining the model architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 200064):
+            Vocabulary size of the Phi-4-MM model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`Phi4MMModel`].
+        hidden_size (`int`, *optional*, defaults to 3072):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 8192):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        resid_pdrop (`float`, *optional*, defaults to 0.0):
+            Dropout probability for mlp outputs.
+        embd_pdrop (`int`, *optional*, defaults to 0.0):
+            The dropout ratio for the embeddings.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio after computing the attention scores.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 4096):
+            The maximum sequence length that this model might ever be used with.
+        original_max_position_embeddings (`int`, *optional*, defaults to 4096):
+            The maximum sequence length that this model was trained with. This is used to determine the size of the
+            original RoPE embeddings when using long scaling.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-05):
+            The epsilon value used for the RMSNorm.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`dict`, *optional*):
+            The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
+            contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
+            the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
+            divided by the number of attention heads divided by 2.
+        partial_rotary_factor (`float`, *optional*, defaults to 0.5):
+            Percentage of the query and keys which will have rotary embedding.
+        bos_token_id (`int`, *optional*, defaults to 199999):
+            The id of the "beginning-of-sequence" token.
+        eos_token_id (`int`, *optional*, defaults to 199999):
+            The id of the "end-of-sequence" token.
+        pad_token_id (`int`, *optional*, defaults to 199999):
+            The id of the padding token.
+        sliding_window (`int`, *optional*):
+            Sliding window attention window size. If `None`, no sliding window is applied.
+
+    Example:
+
+    ```python
+    >>> from transformers import Phi4MMModel, Phi4MMConfig
+
+    >>> # Initializing a Phi-4-MM style configuration
+    >>> configuration = Phi4MMConfig.from_pretrained("TBA")
+
+    >>> # Initializing a model from the configuration
+    >>> model = Phi4MMModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "phi4mm"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=200064,
+        hidden_size=3072,
+        intermediate_size=8192,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        resid_pdrop=0.0,
+        embd_pdrop=0.0,
+        attention_dropout=0.0,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        original_max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-5,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        partial_rotary_factor=1,
+        bos_token_id=199999,
+        eos_token_id=199999,
+        pad_token_id=199999,
+        sliding_window=None,
+        embd_layer: str = "default",
+        img_processor=None,
+        audio_processor=None,
+        vision_lora=None,
+        speech_lora=None,
+        **kwargs,
+    ):
+        self.embd_layer = embd_layer
+        self.img_processor = img_processor
+        self.audio_processor = audio_processor
+        self.vision_lora = vision_lora
+        self.speech_lora = speech_lora
+
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.resid_pdrop = resid_pdrop
+        self.embd_pdrop = embd_pdrop
+        self.attention_dropout = attention_dropout
+        self.hidden_act = hidden_act
+        self.max_position_embeddings = max_position_embeddings
+        self.original_max_position_embeddings = original_max_position_embeddings
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.partial_rotary_factor = partial_rotary_factor
+        self._rope_scaling_adjustment()
+        self._rope_scaling_validation()
+        self.sliding_window = sliding_window
+
+        super().__init__(
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            pad_token_id=pad_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+    def _rope_scaling_adjustment(self):
+        """
+        Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
+        """
+        if self.rope_scaling is None:
+            return
+
+        rope_scaling_type = self.rope_scaling.get("type", None)
+
+        # For backward compatibility if previous version used "su" or "yarn"
+        if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
+            self.rope_scaling["type"] = "longrope"
+
+    def _rope_scaling_validation(self):
+        """
+        Validate the `rope_scaling` configuration.
+        """
+        if self.rope_scaling is None:
+            return
+
+        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
+            raise ValueError(
+                "`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
+                f"got {self.rope_scaling}"
+            )
+        rope_scaling_type = self.rope_scaling.get("type", None)
+        rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
+        rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
+        if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
+            raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
+        if not (
+            isinstance(rope_scaling_short_factor, list)
+            and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
+        ):
+            raise ValueError(
+                f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
+            )
+        rotary_ndims = int(self.hidden_size // self.num_attention_heads * self.partial_rotary_factor)
+        if not len(rope_scaling_short_factor) == rotary_ndims // 2:
+            raise ValueError(
+                f"`rope_scaling`'s short_factor field must have length {rotary_ndims // 2}, got {len(rope_scaling_short_factor)}"
+            )
+        if not (
+            isinstance(rope_scaling_long_factor, list)
+            and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
+        ):
+            raise ValueError(
+                f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
+            )
+        if not len(rope_scaling_long_factor) == rotary_ndims // 2:
+            raise ValueError(
+                f"`rope_scaling`'s long_factor field must have length {rotary_ndims // 2}, got {len(rope_scaling_long_factor)}"
+            )

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 199999,
+  "eos_token_id": [
+    200020,
+    199999
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.51.0"
+}

openvino_audio_embeddings_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c098aea6eeb8c3c8c66c17b1cf7decdd4bd0399451a26f701d9ebeb36458e8
+size 640

openvino_audio_embeddings_model.xml

@@ -0,0 +1,128 @@
+<?xml version="1.0"?>
+<net name="Model0" version="11">
+	<layers>
+		<layer id="0" name="input_" type="Parameter" version="opset1">
+			<data shape="?,?,80" element_type="f32" />
+			<output>
+				<port id="0" precision="FP32" names="input_">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>80</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Constant_2102" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 80" offset="0" size="320" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>80</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Multiply_2090" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>80</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>80</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>80</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Constant_2103" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 80" offset="320" size="320" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>80</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="aten::mul/Multiply" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>80</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>80</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="last_hidden_state">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>80</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="Result_44" type="Result" version="opset1" output_names="last_hidden_state">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>80</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="1" />
+		<edge from-layer="2" from-port="2" to-layer="4" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
+		<edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<version value="2.19.0" />
+			<weight_compression>
+				<advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<backup_mode value="int8_asym" />
+				<compression_format value="dequantize" />
+				<gptq value="False" />
+				<group_size value="-1" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int8_sym" />
+				<ratio value="1.0" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<nncf_version value="2.19.0" />
+			<optimum_intel_version value="1.27.0.dev0+132f70d" />
+			<optimum_version value="2.1.0.dev0" />
+			<pytorch_version value="2.9.1+cpu" />
+			<transformers_version value="4.51.0" />
+		</optimum>
+	</rt_info>
+</net>

openvino_audio_encoder_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c4ea42f504a9f391f770ffdcf2d747dbe4b62dbfb908b3d10084fee8416ccc
+size 431597364

openvino_audio_forward_embeddings_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85cd06a467fd6cc9616c6d531ebdf092c8149395b624fcdf1dab7511d0bc1098
+size 12647472

openvino_audio_forward_embeddings_model.xml

@@ -0,0 +1,1123 @@
+<?xml version="1.0"?>
+<net name="Model6" version="11">
+	<layers>
+		<layer id="0" name="audio_input" type="Parameter" version="opset1">
+			<data shape="?,?,80" element_type="f32" />
+			<output>
+				<port id="0" precision="FP32" names="audio_input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>80</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="11" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I64" names="11" />
+			</output>
+		</layer>
+		<layer id="2" name="__module.embed/aten::unsqueeze/Unsqueeze" type="Unsqueeze" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>80</dim>
+				</port>
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="14,input.1">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>80</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="self.embed.conv.0.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="1024, 1, 3, 3" offset="8" size="9216" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Convert_2965993" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="self.embed.conv.0.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1024, 1, 1, 1" offset="9224" size="2048" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="self.embed.conv.0.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="self.embed.conv.0.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="__module.embed.conv.0/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="2, 2" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1</dim>
+					<dim>-1</dim>
+					<dim>80</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>40</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="__module.embed.conv.0/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1024, 1, 1" offset="11272" size="4096" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="__module.embed.conv.0/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>40</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="26,input.3">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>40</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="__module.embed.conv.1/aten::relu/Relu" type="ReLU" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>40</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="27,input.5">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>40</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="__module.embed.conv.2/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="i8" shape="1024, 1, 1, 3, 3" offset="15368" size="9216" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="13" name="Convert_2966000" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="__module.embed.conv.2/aten::_convolution/Reshape/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1024, 1, 1, 1, 1" offset="24584" size="2048" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="__module.embed.conv.2/aten::_convolution/Reshape/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="__module.embed.conv.2/aten::_convolution/Reshape/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="__module.embed.conv.2/aten::_convolution/GroupConvolution" type="GroupConvolution" version="opset1">
+			<data strides="2, 2" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>40</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="__module.embed.conv.2/aten::_convolution/Reshape_1" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1024, 1, 1" offset="26632" size="4096" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="__module.embed.conv.2/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="34,input.7">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="self.embed.conv.3.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="1024, 1024, 1, 1" offset="30728" size="1048576" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="Convert_2961244" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="self.embed.conv.3.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1024, 1, 1, 1" offset="1079304" size="2048" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="23" name="self.embed.conv.3.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="24" name="self.embed.conv.3.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="__module.embed.conv.3/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="26" name="__module.embed.conv.3/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1024, 1, 1" offset="1081352" size="4096" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="27" name="__module.embed.conv.3/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="41,input.9">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="28" name="__module.embed.conv.1/aten::relu/Relu_1" type="ReLU" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="42,input.11">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="29" name="__module.embed.conv.5/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="i8" shape="1024, 1, 1, 3, 3" offset="1085448" size="9216" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="30" name="Convert_2966007" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="31" name="__module.embed.conv.5/aten::_convolution/Reshape/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1024, 1, 1, 1, 1" offset="1094664" size="2048" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="32" name="__module.embed.conv.5/aten::_convolution/Reshape/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="33" name="__module.embed.conv.5/aten::_convolution/Reshape/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="34" name="__module.embed.conv.5/aten::_convolution/GroupConvolution" type="GroupConvolution" version="opset1">
+			<data strides="2, 2" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>20</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3</dim>
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>10</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="35" name="__module.embed.conv.5/aten::_convolution/Reshape_1" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1024, 1, 1" offset="1096712" size="4096" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="36" name="__module.embed.conv.5/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>10</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="49,input.13">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>10</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="37" name="self.embed.conv.6.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="1024, 1024, 1, 1" offset="1100808" size="1048576" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="38" name="Convert_2965986" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="39" name="self.embed.conv.6.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1024, 1, 1, 1" offset="2149384" size="2048" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="40" name="self.embed.conv.6.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="41" name="self.embed.conv.6.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="42" name="__module.embed.conv.6/aten::_convolution/Convolution" type="Convolution" version="opset1">
+			<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>10</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>10</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="43" name="__module.embed.conv.6/aten::_convolution/Reshape" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1024, 1, 1" offset="2151432" size="4096" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="44" name="__module.embed.conv.6/aten::_convolution/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>10</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1024</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="56,input">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>10</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="45" name="__module.embed.conv.1/aten::relu/Relu_2" type="ReLU" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>10</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="57,x">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>10</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="46" name="__module.embed/aten::transpose/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="4" offset="2155528" size="16" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="47" name="__module.embed/aten::transpose/Transpose" type="Transpose" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>-1</dim>
+					<dim>10</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="60">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>10</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="48" name="Constant_97793" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="2155544" size="24" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="49" name="__module.embed/aten::reshape/Reshape" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1024</dim>
+					<dim>10</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="62">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>10240</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="50" name="self.embed.out.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="1024, 10240" offset="2155568" size="10485760" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>10240</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="51" name="Convert_2956502" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>1024</dim>
+					<dim>10240</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>10240</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="52" name="self.embed.out.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="1024, 1" offset="12641328" size="2048" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="53" name="self.embed.out.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>10240</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1024</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>1024</dim>
+					<dim>10240</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="54" name="self.embed.out.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1024</dim>
+					<dim>10240</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>10240</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="55" name="__module.embed.out/ov_ext::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>10240</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1024</dim>
+					<dim>10240</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="56" name="Constant_97783" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1024" offset="12643376" size="4096" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="57" name="__module.embed.out/ov_ext::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1024</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1024</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="last_hidden_state">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="58" name="Result_95416" type="Result" version="opset1" output_names="last_hidden_state">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1024</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="1" />
+		<edge from-layer="2" from-port="2" to-layer="8" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
+		<edge from-layer="4" from-port="1" to-layer="6" to-port="0" />
+		<edge from-layer="5" from-port="0" to-layer="6" to-port="1" />
+		<edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
+		<edge from-layer="7" from-port="1" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="2" to-layer="10" to-port="0" />
+		<edge from-layer="9" from-port="0" to-layer="10" to-port="1" />
+		<edge from-layer="10" from-port="2" to-layer="11" to-port="0" />
+		<edge from-layer="11" from-port="1" to-layer="17" to-port="0" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="0" />
+		<edge from-layer="13" from-port="1" to-layer="15" to-port="0" />
+		<edge from-layer="14" from-port="0" to-layer="15" to-port="1" />
+		<edge from-layer="15" from-port="2" to-layer="16" to-port="0" />
+		<edge from-layer="16" from-port="1" to-layer="17" to-port="1" />
+		<edge from-layer="17" from-port="2" to-layer="19" to-port="0" />
+		<edge from-layer="18" from-port="0" to-layer="19" to-port="1" />
+		<edge from-layer="19" from-port="2" to-layer="25" to-port="0" />
+		<edge from-layer="20" from-port="0" to-layer="21" to-port="0" />
+		<edge from-layer="21" from-port="1" to-layer="23" to-port="0" />
+		<edge from-layer="22" from-port="0" to-layer="23" to-port="1" />
+		<edge from-layer="23" from-port="2" to-layer="24" to-port="0" />
+		<edge from-layer="24" from-port="1" to-layer="25" to-port="1" />
+		<edge from-layer="25" from-port="2" to-layer="27" to-port="0" />
+		<edge from-layer="26" from-port="0" to-layer="27" to-port="1" />
+		<edge from-layer="27" from-port="2" to-layer="28" to-port="0" />
+		<edge from-layer="28" from-port="1" to-layer="34" to-port="0" />
+		<edge from-layer="29" from-port="0" to-layer="30" to-port="0" />
+		<edge from-layer="30" from-port="1" to-layer="32" to-port="0" />
+		<edge from-layer="31" from-port="0" to-layer="32" to-port="1" />
+		<edge from-layer="32" from-port="2" to-layer="33" to-port="0" />
+		<edge from-layer="33" from-port="1" to-layer="34" to-port="1" />
+		<edge from-layer="34" from-port="2" to-layer="36" to-port="0" />
+		<edge from-layer="35" from-port="0" to-layer="36" to-port="1" />
+		<edge from-layer="36" from-port="2" to-layer="42" to-port="0" />
+		<edge from-layer="37" from-port="0" to-layer="38" to-port="0" />
+		<edge from-layer="38" from-port="1" to-layer="40" to-port="0" />
+		<edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
+		<edge from-layer="40" from-port="2" to-layer="41" to-port="0" />
+		<edge from-layer="41" from-port="1" to-layer="42" to-port="1" />
+		<edge from-layer="42" from-port="2" to-layer="44" to-port="0" />
+		<edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
+		<edge from-layer="44" from-port="2" to-layer="45" to-port="0" />
+		<edge from-layer="45" from-port="1" to-layer="47" to-port="0" />
+		<edge from-layer="46" from-port="0" to-layer="47" to-port="1" />
+		<edge from-layer="47" from-port="2" to-layer="49" to-port="0" />
+		<edge from-layer="48" from-port="0" to-layer="49" to-port="1" />
+		<edge from-layer="49" from-port="2" to-layer="55" to-port="0" />
+		<edge from-layer="50" from-port="0" to-layer="51" to-port="0" />
+		<edge from-layer="51" from-port="1" to-layer="53" to-port="0" />
+		<edge from-layer="52" from-port="0" to-layer="53" to-port="1" />
+		<edge from-layer="53" from-port="2" to-layer="54" to-port="0" />
+		<edge from-layer="54" from-port="1" to-layer="55" to-port="1" />
+		<edge from-layer="55" from-port="2" to-layer="57" to-port="0" />
+		<edge from-layer="56" from-port="0" to-layer="57" to-port="1" />
+		<edge from-layer="57" from-port="2" to-layer="58" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<version value="2.19.0" />
+			<weight_compression>
+				<advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<backup_mode value="int8_asym" />
+				<compression_format value="dequantize" />
+				<gptq value="False" />
+				<group_size value="-1" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int8_sym" />
+				<ratio value="1.0" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<nncf_version value="2.19.0" />
+			<optimum_intel_version value="1.27.0.dev0+132f70d" />
+			<optimum_version value="2.1.0.dev0" />
+			<pytorch_version value="2.9.1+cpu" />
+			<transformers_version value="4.51.0" />
+		</optimum>
+	</rt_info>
+</net>

openvino_audio_speech_projection_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd876f21e8ef990b4dab2ab8bea52dfe7922a6a1d4112d29b0faa4784b3b0668
+size 12607488

openvino_audio_speech_projection_model.xml

@@ -0,0 +1,366 @@
+<?xml version="1.0"?>
+<net name="Model12" version="11">
+	<layers>
+		<layer id="0" name="input" type="Parameter" version="opset1">
+			<data shape="?,?,1024" element_type="f32" />
+			<output>
+				<port id="0" precision="FP32" names="input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="self.0.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="3072, 1024" offset="0" size="3145728" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Convert_4248226" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="self.0.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="3072, 1" offset="3145728" size="6144" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="self.0.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="__module.0/ov_ext::linear/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="__module.0/ov_ext::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1024</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="self.0.bias" type="Const" version="opset1">
+			<data element_type="bf16" shape="3072" offset="3151872" size="6144" />
+			<output>
+				<port id="0" precision="BF16" names="self.0.bias">
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="__module.0/ov_ext::linear/Convert_1" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="BF16">
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="__module.0/ov_ext::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="11,input_1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="__module.1/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="13">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="self.2.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="3072, 3072" offset="3158016" size="9437184" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="Convert_4243483" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="13" name="self.2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="3072, 1" offset="12595200" size="6144" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="self.2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="__module.2/ov_ext::linear/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="__module.2/ov_ext::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="self.2.bias" type="Const" version="opset1">
+			<data element_type="bf16" shape="3072" offset="12601344" size="6144" />
+			<output>
+				<port id="0" precision="BF16" names="self.2.bias">
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="__module.2/ov_ext::linear/Convert_1" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="BF16">
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="__module.2/ov_ext::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="last_hidden_state">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="Result_100412" type="Result" version="opset1" output_names="last_hidden_state">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="4" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
+		<edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
+		<edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
+		<edge from-layer="6" from-port="2" to-layer="9" to-port="0" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="0" />
+		<edge from-layer="8" from-port="1" to-layer="9" to-port="1" />
+		<edge from-layer="9" from-port="2" to-layer="10" to-port="0" />
+		<edge from-layer="10" from-port="1" to-layer="16" to-port="0" />
+		<edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
+		<edge from-layer="12" from-port="1" to-layer="14" to-port="0" />
+		<edge from-layer="13" from-port="0" to-layer="14" to-port="1" />
+		<edge from-layer="14" from-port="2" to-layer="15" to-port="0" />
+		<edge from-layer="15" from-port="1" to-layer="16" to-port="1" />
+		<edge from-layer="16" from-port="2" to-layer="19" to-port="0" />
+		<edge from-layer="17" from-port="0" to-layer="18" to-port="0" />
+		<edge from-layer="18" from-port="1" to-layer="19" to-port="1" />
+		<edge from-layer="19" from-port="2" to-layer="20" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<version value="2.19.0" />
+			<weight_compression>
+				<advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<backup_mode value="int8_asym" />
+				<compression_format value="dequantize" />
+				<gptq value="False" />
+				<group_size value="-1" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int8_sym" />
+				<ratio value="1.0" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<nncf_version value="2.19.0" />
+			<optimum_intel_version value="1.27.0.dev0+132f70d" />
+			<optimum_version value="2.1.0.dev0" />
+			<pytorch_version value="2.9.1+cpu" />
+			<transformers_version value="4.51.0" />
+		</optimum>
+	</rt_info>
+</net>

openvino_audio_vision_projection_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd876f21e8ef990b4dab2ab8bea52dfe7922a6a1d4112d29b0faa4784b3b0668
+size 12607488

openvino_audio_vision_projection_model.xml

@@ -0,0 +1,366 @@
+<?xml version="1.0"?>
+<net name="Model9" version="11">
+	<layers>
+		<layer id="0" name="input" type="Parameter" version="opset1">
+			<data shape="?,?,1024" element_type="f32" />
+			<output>
+				<port id="0" precision="FP32" names="input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="self.0.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="3072, 1024" offset="0" size="3145728" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Convert_4238719" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="self.0.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="3072, 1" offset="3145728" size="6144" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="self.0.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="__module.0/ov_ext::linear/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="__module.0/ov_ext::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1024</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>1024</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="self.0.bias" type="Const" version="opset1">
+			<data element_type="bf16" shape="3072" offset="3151872" size="6144" />
+			<output>
+				<port id="0" precision="BF16" names="self.0.bias">
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="__module.0/ov_ext::linear/Convert_1" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="BF16">
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="__module.0/ov_ext::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="11,input_1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="__module.1/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="13">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="self.2.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="3072, 3072" offset="3158016" size="9437184" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="Convert_4233976" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="13" name="self.2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="3072, 1" offset="12595200" size="6144" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="self.2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="__module.2/ov_ext::linear/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="__module.2/ov_ext::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="self.2.bias" type="Const" version="opset1">
+			<data element_type="bf16" shape="3072" offset="12601344" size="6144" />
+			<output>
+				<port id="0" precision="BF16" names="self.2.bias">
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="__module.2/ov_ext::linear/Convert_1" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="BF16">
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="__module.2/ov_ext::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="last_hidden_state">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="Result_98102" type="Result" version="opset1" output_names="last_hidden_state">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="4" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
+		<edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
+		<edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
+		<edge from-layer="6" from-port="2" to-layer="9" to-port="0" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="0" />
+		<edge from-layer="8" from-port="1" to-layer="9" to-port="1" />
+		<edge from-layer="9" from-port="2" to-layer="10" to-port="0" />
+		<edge from-layer="10" from-port="1" to-layer="16" to-port="0" />
+		<edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
+		<edge from-layer="12" from-port="1" to-layer="14" to-port="0" />
+		<edge from-layer="13" from-port="0" to-layer="14" to-port="1" />
+		<edge from-layer="14" from-port="2" to-layer="15" to-port="0" />
+		<edge from-layer="15" from-port="1" to-layer="16" to-port="1" />
+		<edge from-layer="16" from-port="2" to-layer="19" to-port="0" />
+		<edge from-layer="17" from-port="0" to-layer="18" to-port="0" />
+		<edge from-layer="18" from-port="1" to-layer="19" to-port="1" />
+		<edge from-layer="19" from-port="2" to-layer="20" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<version value="2.19.0" />
+			<weight_compression>
+				<advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<backup_mode value="int8_asym" />
+				<compression_format value="dequantize" />
+				<gptq value="False" />
+				<group_size value="-1" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int8_sym" />
+				<ratio value="1.0" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<nncf_version value="2.19.0" />
+			<optimum_intel_version value="1.27.0.dev0+132f70d" />
+			<optimum_version value="2.1.0.dev0" />
+			<pytorch_version value="2.9.1+cpu" />
+			<transformers_version value="4.51.0" />
+		</optimum>
+	</rt_info>
+</net>

openvino_config.json

@@ -0,0 +1,43 @@
+{
+  "dtype": "int4",
+  "input_info": null,
+  "optimum_version": "2.1.0.dev0",
+  "quantization_config": {
+    "_dataset_kwargs": {},
+    "dataset": null,
+    "default_config": {
+      "quant_method": "default"
+    },
+    "ignored_scope": null,
+    "num_samples": null,
+    "processor": "microsoft/phi-4-multimodal-instruct",
+    "quantization_configs": {
+      "lm_model": {
+        "_dataset_kwargs": {},
+        "all_layers": null,
+        "backup_precision": null,
+        "bits": 4,
+        "dataset": null,
+        "dq_group_size": null,
+        "dtype": "int4",
+        "gptq": null,
+        "group_size": 64,
+        "group_size_fallback": null,
+        "ignored_scope": null,
+        "lora_correction": null,
+        "num_samples": null,
+        "processor": "microsoft/phi-4-multimodal-instruct",
+        "quant_method": "default",
+        "ratio": 1.0,
+        "scale_estimation": null,
+        "sensitivity_metric": null,
+        "statistics_path": null,
+        "sym": false,
+        "tokenizer": "microsoft/phi-4-multimodal-instruct"
+      }
+    },
+    "tokenizer": "microsoft/phi-4-multimodal-instruct"
+  },
+  "save_onnx_model": false,
+  "transformers_version": "4.51.0"
+}

openvino_detokenizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ce47114b112bcfbd7b232bd32f57b3f19f19c4979b6fd4410aafa2635f9f8f
+size 2998357

openvino_detokenizer.xml

@@ -0,0 +1,218 @@
+<?xml version="1.0"?>
+<net name="detokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_128" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="Parameter_128">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Convert_327" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Constant_130" type="Const" version="opset1">
+			<data element_type="i32" shape="200029" offset="0" size="800116" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>200029</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Constant_132" type="Const" version="opset1">
+			<data element_type="i32" shape="200029" offset="800116" size="800116" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>200029</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_134" type="Const" version="opset1">
+			<data element_type="u8" shape="1398089" offset="1600232" size="1398089" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1398089</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="Slice_139" type="Const" version="opset1">
+			<data element_type="i32" shape="9" offset="2998321" size="36" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>9</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="VocabDecoder_141" type="VocabDecoder" version="extension">
+			<data skip_tokens="" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>200029</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>200029</dim>
+				</port>
+				<port id="3" precision="U8">
+					<dim>1398089</dim>
+				</port>
+				<port id="4" precision="I32">
+					<dim>9</dim>
+				</port>
+			</input>
+			<output>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="FuzeRagged_142" type="FuzeRagged" version="extension">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="UTF8Validate_143" type="UTF8Validate" version="extension">
+			<data replace_mode="true" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="StringTensorPack_144" type="StringTensorPack" version="opset15">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="STRING" names="Result_145,string_output">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="Result_145" type="Result" version="opset1" output_names="Result_145,string_output">
+			<input>
+				<port id="0" precision="STRING">
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
+		<edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
+		<edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
+		<edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
+		<edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
+		<edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
+		<edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
+		<edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
+		<edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
+		<edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
+		<edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
+		<edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
+		<edge from-layer="8" from-port="4" to-layer="9" to-port="1" />
+		<edge from-layer="8" from-port="5" to-layer="9" to-port="2" />
+		<edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
+	</edges>
+	<rt_info>
+		<add_attention_mask value="True" />
+		<add_prefix_space />
+		<add_special_tokens value="True" />
+		<bos_token_id value="199999" />
+		<chat_template value="{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|tool|>' + message['tools'] + '&lt;|/tool|>' + '&lt;|end|>' }}{% else %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>' }}{% else %}{{ eos_token }}{% endif %}" />
+		<clean_up_tokenization_spaces />
+		<detokenizer_input_type value="i64" />
+		<eos_token_id value="199999" />
+		<handle_special_tokens_with_re />
+		<max_length />
+		<number_of_inputs value="1" />
+		<openvino_tokenizers_version value="2025.4.1.0-627-e79796a77f3" />
+		<openvino_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast'>" />
+		<pad_token_id value="199999" />
+		<skip_special_tokens value="True" />
+		<streaming_detokenizer value="False" />
+		<tokenizer_output_type value="i64" />
+		<tokenizers_version value="0.22.2" />
+		<transformers_version value="4.57.3" />
+		<use_max_padding value="False" />
+		<use_sentencepiece_backend value="False" />
+		<utf8_replace_mode value="replace" />
+		<with_detokenizer value="True" />
+	</rt_info>
+</net>

openvino_language_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4172e77c411f21f9c453efca9d324771f4717096100907baa356f35b01e11efa
+size 2601147138

openvino_text_embeddings_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:069b93628617a45d3d5719c7bdbe9f1f8d80f8f9498f927f6d9acc81f12236da
+size 614996740

openvino_text_embeddings_model.xml

@@ -0,0 +1,179 @@
+<?xml version="1.0"?>
+<net name="Model18" version="11">
+	<layers>
+		<layer id="0" name="input" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="self.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="200064, 3072" offset="0" size="614596608" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>200064</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Convert_2190860" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>200064</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>200064</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="self.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="200064, 1" offset="614596608" size="400128" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>200064</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="self.weight/fq_weights_0" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>200064</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>200064</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>200064</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="ov_ext::embedding/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>200064</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>200064</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="ov_ext::embedding/Convert_1" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="ov_ext::embedding/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="614996736" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="8" name="ov_ext::embedding/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>200064</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="FP32" names="inputs_embeds">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="Result_281828" type="Result" version="opset1" output_names="inputs_embeds">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="4" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
+		<edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
+		<edge from-layer="5" from-port="1" to-layer="8" to-port="0" />
+		<edge from-layer="6" from-port="1" to-layer="8" to-port="1" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
+		<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<version value="2.19.0" />
+			<weight_compression>
+				<advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<backup_mode value="int8_asym" />
+				<compression_format value="dequantize" />
+				<gptq value="False" />
+				<group_size value="-1" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int8_sym" />
+				<ratio value="1.0" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<nncf_version value="2.19.0" />
+			<optimum_intel_version value="1.27.0.dev0+132f70d" />
+			<optimum_version value="2.1.0.dev0" />
+			<pytorch_version value="2.9.1+cpu" />
+			<transformers_version value="4.51.0" />
+		</optimum>
+	</rt_info>
+</net>

openvino_tokenizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d28657f94f9cd47a609bb7e2a10f5c1f81341d6970e3c3fd9655db8213b3767
+size 7592501

openvino_tokenizer.xml

@@ -0,0 +1,734 @@
+<?xml version="1.0"?>
+<net name="tokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_1" type="Parameter" version="opset1">
+			<data shape="?" element_type="string" />
+			<output>
+				<port id="0" precision="STRING" names="Parameter_1">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Constant_7" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="2" name="StringTensorUnpack_2" type="StringTensorUnpack" version="opset15">
+			<input>
+				<port id="0" precision="STRING">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="ShapeOf_3" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_4" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="5" name="Constant_5" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="6" name="Gather_6" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="I32" />
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="I64" />
+			</output>
+		</layer>
+		<layer id="7" name="Constant_8" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="4" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="8" name="Range_9" type="Range" version="opset4">
+			<data output_type="i32" />
+			<input>
+				<port id="0" precision="I32" />
+				<port id="1" precision="I64" />
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="Constant_10" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="4" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="10" name="Constant_11" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="11" name="Add_12" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="I64" />
+			</output>
+		</layer>
+		<layer id="12" name="Constant_13" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="4" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="13" name="Range_14" type="Range" version="opset4">
+			<data output_type="i32" />
+			<input>
+				<port id="0" precision="I32" />
+				<port id="1" precision="I64" />
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="Constant_78" type="Const" version="opset1">
+			<data element_type="u8" shape="246" offset="16" size="246" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>246</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="SpecialTokensSplit_79" type="SpecialTokensSplit" version="extension">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="U8">
+					<dim>246</dim>
+				</port>
+			</input>
+			<output>
+				<port id="6" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="10" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="11" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="Constant_81" type="Const" version="opset1">
+			<data element_type="u8" shape="274" offset="262" size="274" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>274</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="RegexSplit_82" type="RegexSplit" version="extension">
+			<data behaviour="remove" invert="true" max_splits="-1" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="U8">
+					<dim>274</dim>
+				</port>
+			</input>
+			<output>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="10" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="11" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="12" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="Constant_84" type="Const" version="opset1">
+			<data element_type="i32" shape="200029" offset="536" size="800116" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>200029</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="Constant_86" type="Const" version="opset1">
+			<data element_type="i32" shape="200029" offset="800652" size="800116" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>200029</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="Constant_88" type="Const" version="opset1">
+			<data element_type="u8" shape="1398089" offset="1600768" size="1398089" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1398089</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="Constant_96" type="Const" version="opset1">
+			<data element_type="i32" shape="199742" offset="2998857" size="798968" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>199742</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="Constant_98" type="Const" version="opset1">
+			<data element_type="i32" shape="199742" offset="3797825" size="798968" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>199742</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="23" name="Constant_100" type="Const" version="opset1">
+			<data element_type="u8" shape="718313" offset="4596793" size="718313" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>718313</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="24" name="Constant_102" type="Const" version="opset1">
+			<data element_type="i32" shape="199742" offset="5315106" size="798968" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>199742</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="Constant_104" type="Const" version="opset1">
+			<data element_type="i32" shape="199742" offset="6114074" size="798968" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>199742</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="26" name="Constant_106" type="Const" version="opset1">
+			<data element_type="u8" shape="679101" offset="6913042" size="679101" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>679101</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="27" name="Constant_90" type="Const" version="opset1">
+			<data element_type="i32" shape="14" offset="7592143" size="56" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>14</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="28" name="Constant_92" type="Const" version="opset1">
+			<data element_type="i32" shape="14" offset="7592199" size="56" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>14</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="29" name="Constant_94" type="Const" version="opset1">
+			<data element_type="u8" shape="164" offset="7592255" size="164" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>164</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="30" name="Constant_107" type="Const" version="opset1">
+			<data element_type="i32" shape="14" offset="7592419" size="56" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>14</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="31" name="BPETokenizer_108" type="BPETokenizer" version="extension">
+			<data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="40003" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>200029</dim>
+				</port>
+				<port id="6" precision="I32">
+					<dim>200029</dim>
+				</port>
+				<port id="7" precision="U8">
+					<dim>1398089</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>199742</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>199742</dim>
+				</port>
+				<port id="10" precision="U8">
+					<dim>718313</dim>
+				</port>
+				<port id="11" precision="I32">
+					<dim>199742</dim>
+				</port>
+				<port id="12" precision="I32">
+					<dim>199742</dim>
+				</port>
+				<port id="13" precision="U8">
+					<dim>679101</dim>
+				</port>
+				<port id="14" precision="I32">
+					<dim>14</dim>
+				</port>
+				<port id="15" precision="I32">
+					<dim>14</dim>
+				</port>
+				<port id="16" precision="U8">
+					<dim>164</dim>
+				</port>
+				<port id="17" precision="I32">
+					<dim>14</dim>
+				</port>
+			</input>
+			<output>
+				<port id="18" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="19" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="20" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="32" name="Constant_109" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="7592475" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="33" name="Constant_111" type="Const" version="opset1">
+			<data element_type="u8" shape="5" offset="7592479" size="5" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>5</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="34" name="Constant_113" type="Const" version="opset1">
+			<data element_type="u8" shape="13" offset="7592484" size="13" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>13</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="35" name="Truncate_114" type="Truncate" version="extension">
+			<data m_num_inputs="1" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32" />
+				<port id="4" precision="U8">
+					<dim>5</dim>
+				</port>
+				<port id="5" precision="U8">
+					<dim>13</dim>
+				</port>
+			</input>
+			<output>
+				<port id="6" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="36" name="Constant_115" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="37" name="CombineSegments_116" type="CombineSegments" version="extension">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="38" name="Subtract_117" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="39" name="Constant_118" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="40" name="ReduceMax_119" type="ReduceMax" version="opset1">
+			<data keep_dims="false" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32" />
+			</input>
+			<output>
+				<port id="2" precision="I32" />
+			</output>
+		</layer>
+		<layer id="41" name="Constant_120" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="7592497" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="42" name="RaggedToDense_121" type="RaggedToDense" version="extension">
+			<data pad_right="true" m_pad_max_length="false" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32" />
+				<port id="4" precision="I32" />
+			</input>
+			<output>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="43" name="Convert_122" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="44" name="Convert_122.0" type="Convert" version="opset1">
+			<data destination_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="attention_mask">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="46" name="RaggedToDense_121.0" type="Convert" version="opset1">
+			<data destination_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="input_ids">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="47" name="Result_125" type="Result" version="opset1" output_names="input_ids">
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+		<layer id="45" name="Result_127" type="Result" version="opset1" output_names="attention_mask">
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
+		<edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
+		<edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
+		<edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
+		<edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
+		<edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
+		<edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
+		<edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
+		<edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
+		<edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
+		<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
+		<edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
+		<edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
+		<edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
+		<edge from-layer="15" from-port="6" to-layer="17" to-port="0" />
+		<edge from-layer="15" from-port="7" to-layer="17" to-port="1" />
+		<edge from-layer="15" from-port="8" to-layer="17" to-port="2" />
+		<edge from-layer="15" from-port="9" to-layer="17" to-port="3" />
+		<edge from-layer="15" from-port="10" to-layer="17" to-port="4" />
+		<edge from-layer="15" from-port="11" to-layer="17" to-port="5" />
+		<edge from-layer="16" from-port="0" to-layer="17" to-port="6" />
+		<edge from-layer="17" from-port="7" to-layer="31" to-port="0" />
+		<edge from-layer="17" from-port="8" to-layer="31" to-port="1" />
+		<edge from-layer="17" from-port="9" to-layer="31" to-port="2" />
+		<edge from-layer="17" from-port="10" to-layer="31" to-port="3" />
+		<edge from-layer="17" from-port="11" to-layer="31" to-port="4" />
+		<edge from-layer="18" from-port="0" to-layer="31" to-port="5" />
+		<edge from-layer="19" from-port="0" to-layer="31" to-port="6" />
+		<edge from-layer="20" from-port="0" to-layer="31" to-port="7" />
+		<edge from-layer="21" from-port="0" to-layer="31" to-port="8" />
+		<edge from-layer="22" from-port="0" to-layer="31" to-port="9" />
+		<edge from-layer="23" from-port="0" to-layer="31" to-port="10" />
+		<edge from-layer="24" from-port="0" to-layer="31" to-port="11" />
+		<edge from-layer="25" from-port="0" to-layer="31" to-port="12" />
+		<edge from-layer="26" from-port="0" to-layer="31" to-port="13" />
+		<edge from-layer="27" from-port="0" to-layer="31" to-port="14" />
+		<edge from-layer="28" from-port="0" to-layer="31" to-port="15" />
+		<edge from-layer="29" from-port="0" to-layer="31" to-port="16" />
+		<edge from-layer="30" from-port="0" to-layer="31" to-port="17" />
+		<edge from-layer="31" from-port="18" to-layer="35" to-port="0" />
+		<edge from-layer="31" from-port="19" to-layer="35" to-port="1" />
+		<edge from-layer="31" from-port="20" to-layer="35" to-port="2" />
+		<edge from-layer="32" from-port="0" to-layer="35" to-port="3" />
+		<edge from-layer="33" from-port="0" to-layer="35" to-port="4" />
+		<edge from-layer="34" from-port="0" to-layer="35" to-port="5" />
+		<edge from-layer="35" from-port="6" to-layer="37" to-port="0" />
+		<edge from-layer="35" from-port="7" to-layer="37" to-port="1" />
+		<edge from-layer="35" from-port="8" to-layer="37" to-port="2" />
+		<edge from-layer="36" from-port="0" to-layer="37" to-port="3" />
+		<edge from-layer="37" from-port="5" to-layer="38" to-port="0" />
+		<edge from-layer="37" from-port="4" to-layer="38" to-port="1" />
+		<edge from-layer="37" from-port="4" to-layer="42" to-port="0" />
+		<edge from-layer="37" from-port="5" to-layer="42" to-port="1" />
+		<edge from-layer="37" from-port="6" to-layer="42" to-port="2" />
+		<edge from-layer="38" from-port="2" to-layer="40" to-port="0" />
+		<edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
+		<edge from-layer="40" from-port="2" to-layer="42" to-port="3" />
+		<edge from-layer="41" from-port="0" to-layer="42" to-port="4" />
+		<edge from-layer="42" from-port="6" to-layer="43" to-port="0" />
+		<edge from-layer="42" from-port="5" to-layer="46" to-port="0" />
+		<edge from-layer="43" from-port="1" to-layer="44" to-port="0" />
+		<edge from-layer="44" from-port="1" to-layer="45" to-port="0" />
+		<edge from-layer="46" from-port="1" to-layer="47" to-port="0" />
+	</edges>
+	<rt_info>
+		<add_attention_mask value="True" />
+		<add_prefix_space />
+		<add_special_tokens value="True" />
+		<bos_token_id value="199999" />
+		<chat_template value="{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|tool|>' + message['tools'] + '&lt;|/tool|>' + '&lt;|end|>' }}{% else %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>' }}{% else %}{{ eos_token }}{% endif %}" />
+		<clean_up_tokenization_spaces />
+		<detokenizer_input_type value="i64" />
+		<eos_token_id value="199999" />
+		<handle_special_tokens_with_re />
+		<max_length />
+		<number_of_inputs value="1" />
+		<openvino_tokenizers_version value="2025.4.1.0-627-e79796a77f3" />
+		<openvino_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast'>" />
+		<pad_token_id value="199999" />
+		<skip_special_tokens value="True" />
+		<streaming_detokenizer value="False" />
+		<tokenizer_output_type value="i64" />
+		<tokenizers_version value="0.22.2" />
+		<transformers_version value="4.57.3" />
+		<use_max_padding value="False" />
+		<use_sentencepiece_backend value="False" />
+		<utf8_replace_mode value="replace" />
+		<with_detokenizer value="True" />
+	</rt_info>
+</net>

openvino_vision_embeddings_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8652db47d1521867a714125a5216013ab1c9a12b3ffef651961a2938471c87
+size 399761132

openvino_vision_projection_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d77053d6ba3be941efc10ec1adbb1f7d969ad631fb31ce7a6c15ba7fe45fd7
+size 13012992

openvino_vision_projection_model.xml

@@ -0,0 +1,334 @@
+<?xml version="1.0"?>
+<net name="Model21" version="11">
+	<layers>
+		<layer id="0" name="input" type="Parameter" version="opset1">
+			<data shape="?,?,1152" element_type="f32" />
+			<output>
+				<port id="0" precision="FP32" names="input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1152</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="self.0.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="3072, 1152" offset="0" size="3538944" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>1152</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Convert_2951735" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>1152</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>1152</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="self.0.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="3072, 1" offset="3538944" size="6144" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="self.0.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1152</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>3072</dim>
+					<dim>1152</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="self.0.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1152</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>1152</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="__module.0/ov_ext::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1152</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>1152</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="Constant_286148" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 3072" offset="3545088" size="12288" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="__module.0/ov_ext::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="11,input_1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="__module.1/aten::gelu/Gelu" type="Gelu" version="opset7">
+			<data approximation_mode="ERF" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32" names="13">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="self.2.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="3072, 3072" offset="3557376" size="9437184" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="Convert_2946993" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="self.2.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="3072, 1" offset="12994560" size="6144" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="13" name="self.2.weight/fq_weights_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>3072</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="self.2.weight/fq_weights_1/convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="__module.2/ov_ext::linear/MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>3072</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="Constant_286149" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 3072" offset="13000704" size="12288" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="__module.2/ov_ext::linear/Add" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32" names="last_hidden_state">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="Result_284126" type="Result" version="opset1" output_names="last_hidden_state">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>3072</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="4" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
+		<edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
+		<edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
+		<edge from-layer="6" from-port="2" to-layer="8" to-port="0" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="2" to-layer="9" to-port="0" />
+		<edge from-layer="9" from-port="1" to-layer="15" to-port="0" />
+		<edge from-layer="10" from-port="0" to-layer="11" to-port="0" />
+		<edge from-layer="11" from-port="1" to-layer="13" to-port="0" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="1" />
+		<edge from-layer="13" from-port="2" to-layer="14" to-port="0" />
+		<edge from-layer="14" from-port="1" to-layer="15" to-port="1" />
+		<edge from-layer="15" from-port="2" to-layer="17" to-port="0" />
+		<edge from-layer="16" from-port="0" to-layer="17" to-port="1" />
+		<edge from-layer="17" from-port="2" to-layer="18" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<version value="2.19.0" />
+			<weight_compression>
+				<advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<backup_mode value="int8_asym" />
+				<compression_format value="dequantize" />
+				<gptq value="False" />
+				<group_size value="-1" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int8_sym" />
+				<ratio value="1.0" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<nncf_version value="2.19.0" />
+			<optimum_intel_version value="1.27.0.dev0+132f70d" />
+			<optimum_version value="2.1.0.dev0" />
+			<pytorch_version value="2.9.1+cpu" />
+			<transformers_version value="4.51.0" />
+		</optimum>
+	</rt_info>
+</net>

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "audio_compression_rate": 8,
+  "audio_downsample_rate": 1,
+  "audio_feat_stride": 1,
+  "auto_map": {
+    "AutoFeatureExtractor": "microsoft/phi-4-multimodal-instruct--processing_phi4mm.Phi4MMAudioFeatureExtractor",
+    "AutoImageProcessor": "microsoft/phi-4-multimodal-instruct--processing_phi4mm.Phi4MMImageProcessor",
+    "AutoProcessor": "microsoft/phi-4-multimodal-instruct--processing_phi4mm.Phi4MMProcessor"
+  },
+  "dynamic_hd": 36,
+  "image_processor_type": "Phi4MMImageProcessor",
+  "processor_class": "Phi4MMProcessor"
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c1b9f641d4f8b7247b8d5007dd3b6a9f6a87cb5123134fe0d326f14d10c0585
+size 15524479

tokenizer_config.json

@@ -0,0 +1,127 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<|endoftext10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<|endoftext11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Phi4MMProcessor",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}