Upload folder using huggingface_hub

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+license_link: https://choosealicense.com/licenses/mit/
+base_model:
+- microsoft/Phi-3-mini-4k-instruct
+base_model_relation: quantized
+---
+# Phi-3-mini-4k-instruct-int4-cw-ov
+* Model creator: [Microsoft](https://huggingface.co/microsoft)
+ * Original model: [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
+
+## Description
+This is [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT4 by [NNCF](https://github.com/openvinotoolkit/nncf).
+
+> [!NOTE]  
+> The model is optimized for inference on NPU using these [instructions.](https://docs.openvino.ai/2025/openvino-workflow-generative/inference-with-genai/inference-with-genai-on-npu.html#export-an-llm-model-via-hugging-face-optimum-intel)
+
+## Quantization Parameters
+
+Weight compression was performed using `nncf.compress_weights` with the following parameters:
+
+* mode: **int4_asym**
+* ratio: **1**
+
+For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2024/openvino-workflow/model-optimization-guide/weight-compression.html).
+
+## Compatibility
+
+The provided OpenVINO™ IR model is compatible with:
+
+* OpenVINO version 2024.4.0 and higher
+
+## Running Model Inference with [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai)
+
+1. Install packages required for using OpenVINO GenAI.
+```
+pip install openvino-genai huggingface_hub
+```
+
+2. Download model from HuggingFace Hub
+   
+```
+import huggingface_hub as hf_hub
+
+model_id = "OpenVINO/Phi-3-mini-4k-instruct-int4-cw-ov"
+model_path = "Phi-3-mini-4k-instruct-int4-cw-ov"
+
+hf_hub.snapshot_download(model_id, local_dir=model_path)
+
+```
+
+3. Run model inference:
+
+```
+import openvino_genai as ov_genai
+
+device = "NPU"
+pipe = ov_genai.LLMPipeline(model_path, device)
+print(pipe.generate("What is OpenVINO?", max_length=200))
+```
+
+More GenAI usage examples can be found in OpenVINO GenAI library [docs](https://github.com/openvinotoolkit/openvino.genai/blob/master/src/README.md) and [samples](https://github.com/openvinotoolkit/openvino.genai?tab=readme-ov-file#openvino-genai-samples)
+
+## Limitations
+
+Check the original model card for [original model card](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) for limitations.
+
+## Legal information
+
+The original model is distributed under [mit](https://choosealicense.com/licenses/mit/) license. More details can be found in [original model card](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
+
+## Disclaimer
+
+Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See [Intel’s Global Human Rights Principles](https://www.intel.com/content/dam/www/central-libraries/us/en/documents/policy-human-rights.pdf). Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 32064
+}

configuration_phi3.py

@@ -0,0 +1,227 @@
+# 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-3 model configuration"""
+
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
+    "microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
+    "microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
+}
+
+
+class Phi3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the
+    [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
+
+    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 32064):
+            Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`Phi3Model`].
+        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.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            The id of the "beginning-of-sequence" token.
+        eos_token_id (`int`, *optional*, defaults to 32000):
+            The id of the "end-of-sequence" token.
+        pad_token_id (`int`, *optional*, defaults to 32000):
+            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 Phi3Model, Phi3Config
+
+    >>> # Initializing a Phi-3 style configuration
+    >>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
+
+    >>> # Initializing a model from the configuration
+    >>> model = Phi3Model(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "phi3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=32064,
+        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,
+        bos_token_id=1,
+        eos_token_id=32000,
+        pad_token_id=32000,
+        sliding_window=None,
+        **kwargs,
+    ):
+        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._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}"
+            )
+        if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
+            raise ValueError(
+                f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 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) == self.hidden_size // self.num_attention_heads // 2:
+            raise ValueError(
+                f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
+            )

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.51.3"
+}

openvino_detokenizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03033c0408d4ab0211cc6ebed4996eba143e9eb7ff87cce30d46beb111c411d7
+size 467235

openvino_detokenizer.xml

@@ -0,0 +1,353 @@
+<?xml version="1.0"?>
+<net name="detokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_158818" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="Parameter_158818">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Convert_159013" 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_158774" type="Const" version="opset1">
+			<data element_type="i32" shape="32011" offset="0" size="128044" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>32011</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Constant_158776" type="Const" version="opset1">
+			<data element_type="i32" shape="32011" offset="128044" size="128044" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>32011</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_158778" type="Const" version="opset1">
+			<data element_type="u8" shape="211088" offset="256088" size="211088" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>211088</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="Slice_158823" type="Const" version="opset1">
+			<data element_type="i32" shape="13" offset="467176" size="52" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>13</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="VocabDecoder_158825" 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>32011</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>32011</dim>
+				</port>
+				<port id="3" precision="U8">
+					<dim>211088</dim>
+				</port>
+				<port id="4" precision="I32">
+					<dim>13</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="Constant_158827" type="Const" version="opset1">
+			<data element_type="u8" shape="3" offset="467228" size="3" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="Constant_158829" type="Const" version="opset1">
+			<data element_type="u8" shape="1" offset="467231" size="1" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="RegexNormalization_158830" type="RegexNormalization" version="extension">
+			<data global_replace="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>
+				<port id="3" precision="U8">
+					<dim>3</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>1</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="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="ByteFallback_158831" type="ByteFallback" 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="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="11" name="FuzeRagged_158832" 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="12" name="Constant_158834" type="Const" version="opset1">
+			<data element_type="u8" shape="2" offset="467232" size="2" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="13" name="Constant_158836" type="Const" version="opset1">
+			<data element_type="u8" shape="0" offset="467234" size="1" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>0</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="RegexNormalization_158837" type="RegexNormalization" version="extension">
+			<data global_replace="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>
+				<port id="3" precision="U8">
+					<dim>2</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>0</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="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="UTF8Validate_158838" 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="16" name="StringTensorPack_158839" 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_158840,string_output">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="Result_158840" type="Result" version="opset1" output_names="Result_158840,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="6" to-layer="11" to-port="1" />
+		<edge from-layer="6" from-port="5" to-layer="11" to-port="0" />
+		<edge from-layer="6" from-port="8" to-layer="9" to-port="1" />
+		<edge from-layer="6" from-port="7" to-layer="9" to-port="0" />
+		<edge from-layer="6" from-port="9" to-layer="9" to-port="2" />
+		<edge from-layer="7" from-port="0" to-layer="9" to-port="3" />
+		<edge from-layer="8" from-port="0" to-layer="9" to-port="4" />
+		<edge from-layer="9" from-port="5" to-layer="10" to-port="0" />
+		<edge from-layer="9" from-port="6" to-layer="10" to-port="1" />
+		<edge from-layer="9" from-port="7" to-layer="10" to-port="2" />
+		<edge from-layer="10" from-port="3" to-layer="11" to-port="2" />
+		<edge from-layer="10" from-port="4" to-layer="11" to-port="3" />
+		<edge from-layer="10" from-port="5" to-layer="14" to-port="2" />
+		<edge from-layer="11" from-port="5" to-layer="14" to-port="1" />
+		<edge from-layer="11" from-port="4" to-layer="14" to-port="0" />
+		<edge from-layer="12" from-port="0" to-layer="14" to-port="3" />
+		<edge from-layer="13" from-port="0" to-layer="14" to-port="4" />
+		<edge from-layer="14" from-port="5" to-layer="15" to-port="0" />
+		<edge from-layer="14" from-port="6" to-layer="15" to-port="1" />
+		<edge from-layer="14" from-port="7" to-layer="15" to-port="2" />
+		<edge from-layer="15" from-port="3" to-layer="16" to-port="0" />
+		<edge from-layer="15" from-port="4" to-layer="16" to-port="1" />
+		<edge from-layer="15" from-port="5" to-layer="16" to-port="2" />
+		<edge from-layer="16" from-port="3" to-layer="17" to-port="0" />
+	</edges>
+	<rt_info>
+		<add_attention_mask value="True" />
+		<add_prefix_space />
+		<add_special_tokens value="True" />
+		<bos_token_id value="1" />
+		<chat_template value="{% for message in messages %}{% if message['role'] == 'system' %}{{'&lt;|system|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'user' %}{{'&lt;|user|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'assistant' %}{{'&lt;|assistant|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% else %}{{ eos_token }}{% endif %}" />
+		<clean_up_tokenization_spaces />
+		<detokenizer_input_type value="i64" />
+		<eos_token_id value="32000" />
+		<handle_special_tokens_with_re />
+		<max_length />
+		<number_of_inputs value="1" />
+		<openvino_tokenizers_version value="2025.2.0.0-566-85be884a69f" />
+		<openvino_version value="2025.2.0-19136-649eec15cfe-releases/2025/2" />
+		<original_post_processor_template value="{&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}], &quot;pair&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 1}}], &quot;special_tokens&quot;: {}}" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
+		<pad_token_id value="32000" />
+		<processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 1]}}" />
+		<sentencepiece_version value="0.2.0" />
+		<skip_special_tokens value="True" />
+		<streaming_detokenizer value="False" />
+		<tiktoken_version value="0.9.0" />
+		<tokenizer_output_type value="i64" />
+		<tokenizers_version value="0.21.1" />
+		<transformers_version value="4.51.3" />
+		<use_max_padding value="False" />
+		<use_sentencepiece_backend value="False" />
+		<utf8_replace_mode value="replace" />
+		<with_detokenizer value="True" />
+	</rt_info>
+</net>

openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032302e52899ed3d85cd2057c36a40ccc55ca835252414b0bb0ebdeaf0beaeb3
+size 2011963692

openvino_tokenizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7b1340b861821b381655739018a8f45a67531fd4362c76191c5aada08eb29b
+size 1881992

openvino_tokenizer.xml

@@ -0,0 +1,795 @@
+<?xml version="1.0"?>
+<net name="tokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_158686" type="Parameter" version="opset1">
+			<data shape="?" element_type="string" />
+			<output>
+				<port id="0" precision="STRING" names="Parameter_158686">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Constant_158692" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="2" name="StringTensorUnpack_158687" 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_158688" 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_158689" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="5" name="Constant_158690" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="6" name="Gather_158691" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64" />
+			</output>
+		</layer>
+		<layer id="7" name="Constant_158693" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="8" name="Range_158694" type="Range" version="opset4">
+			<data output_type="i32" />
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="Constant_158695" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="10" name="Constant_158696" 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_158697" 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_158698" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="13" name="Range_158699" type="Range" version="opset4">
+			<data output_type="i32" />
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="Constant_158761" type="Const" version="opset1">
+			<data element_type="u8" shape="328" offset="16" size="328" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>328</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="SpecialTokensSplit_158762" 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>328</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_158764" type="Const" version="opset1">
+			<data element_type="u8" shape="13" offset="344" size="13" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>13</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="Constant_158766" type="Const" version="opset1">
+			<data element_type="u8" shape="5" offset="357" size="5" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>5</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="RegexNormalization_158767" type="RegexNormalization" version="extension">
+			<data global_replace="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>
+				<port id="3" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>13</dim>
+				</port>
+				<port id="5" precision="U8">
+					<dim>5</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="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="Constant_158769" type="Const" version="opset1">
+			<data element_type="u8" shape="1" offset="362" size="1" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="Constant_158771" type="Const" version="opset1">
+			<data element_type="u8" shape="3" offset="363" size="3" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="RegexNormalization_158772" type="RegexNormalization" version="extension">
+			<data global_replace="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>
+				<port id="3" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>1</dim>
+				</port>
+				<port id="5" precision="U8">
+					<dim>3</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="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="Constant_158774" type="Const" version="opset1">
+			<data element_type="i32" shape="32011" offset="366" size="128044" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>32011</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="23" name="Constant_158776" type="Const" version="opset1">
+			<data element_type="i32" shape="32011" offset="128410" size="128044" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>32011</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="24" name="Constant_158778" type="Const" version="opset1">
+			<data element_type="u8" shape="211088" offset="256454" size="211088" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>211088</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="Constant_158786" type="Const" version="opset1">
+			<data element_type="i32" shape="61249" offset="467542" size="244996" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>61249</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="26" name="Constant_158788" type="Const" version="opset1">
+			<data element_type="i32" shape="61249" offset="712538" size="244996" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>61249</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="27" name="Constant_158790" type="Const" version="opset1">
+			<data element_type="u8" shape="254123" offset="957534" size="254123" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>254123</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="28" name="Constant_158792" type="Const" version="opset1">
+			<data element_type="i32" shape="61249" offset="1211657" size="244996" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>61249</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="29" name="Constant_158794" type="Const" version="opset1">
+			<data element_type="i32" shape="61249" offset="1456653" size="244996" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>61249</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="30" name="Constant_158796" type="Const" version="opset1">
+			<data element_type="u8" shape="167806" offset="1701649" size="167806" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>167806</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="31" name="Constant_158780" type="Const" version="opset1">
+			<data element_type="i32" shape="475" offset="1869455" size="1900" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>475</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="32" name="Constant_158782" type="Const" version="opset1">
+			<data element_type="i32" shape="475" offset="1871355" size="1900" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>475</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="33" name="Constant_158784" type="Const" version="opset1">
+			<data element_type="u8" shape="6808" offset="1873255" size="6808" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>6808</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="34" name="Constant_158797" type="Const" version="opset1">
+			<data element_type="i32" shape="475" offset="1880063" size="1900" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>475</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="35" name="BPETokenizer_158798" type="BPETokenizer" version="extension">
+			<data unk_token="&lt;unk>" fuse_unk="true" suffix_indicator="" end_suffix="" byte_fallback="true" cache_capacity="20000" />
+			<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>32011</dim>
+				</port>
+				<port id="6" precision="I32">
+					<dim>32011</dim>
+				</port>
+				<port id="7" precision="U8">
+					<dim>211088</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>61249</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>61249</dim>
+				</port>
+				<port id="10" precision="U8">
+					<dim>254123</dim>
+				</port>
+				<port id="11" precision="I32">
+					<dim>61249</dim>
+				</port>
+				<port id="12" precision="I32">
+					<dim>61249</dim>
+				</port>
+				<port id="13" precision="U8">
+					<dim>167806</dim>
+				</port>
+				<port id="14" precision="I32">
+					<dim>475</dim>
+				</port>
+				<port id="15" precision="I32">
+					<dim>475</dim>
+				</port>
+				<port id="16" precision="U8">
+					<dim>6808</dim>
+				</port>
+				<port id="17" precision="I32">
+					<dim>475</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="36" name="Constant_158799" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="1881963" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="37" name="Constant_158801" type="Const" version="opset1">
+			<data element_type="u8" shape="4" offset="1881967" size="4" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="38" name="Constant_158803" type="Const" version="opset1">
+			<data element_type="u8" shape="13" offset="1881971" size="13" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>13</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="39" name="Truncate_158804" 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>4</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="40" name="Constant_158805" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="1881984" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="41" name="CombineSegments_158806" 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="42" name="Subtract_158807" 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="43" name="Constant_158808" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="1881984" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="44" name="ReduceMax_158809" 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="45" name="Constant_158810" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="1881988" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="46" name="RaggedToDense_158811" type="RaggedToDense" version="extension">
+			<data pad_right="false" 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="47" name="Convert_158812" 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="48" name="Convert_158812.0" 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="50" name="RaggedToDense_158811.0" 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="51" name="Result_158815" 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="49" name="Result_158817" 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="3" to-layer="15" to-port="4" />
+		<edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
+		<edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
+		<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="11" to-port="0" />
+		<edge from-layer="6" from-port="3" 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="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="10" to-layer="18" to-port="2" />
+		<edge from-layer="15" from-port="7" to-layer="35" to-port="1" />
+		<edge from-layer="15" from-port="6" to-layer="35" to-port="0" />
+		<edge from-layer="15" from-port="11" to-layer="18" to-port="3" />
+		<edge from-layer="15" from-port="9" to-layer="18" to-port="1" />
+		<edge from-layer="15" from-port="8" to-layer="18" to-port="0" />
+		<edge from-layer="16" from-port="0" to-layer="18" to-port="4" />
+		<edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
+		<edge from-layer="18" from-port="6" to-layer="21" to-port="0" />
+		<edge from-layer="18" from-port="7" to-layer="21" to-port="1" />
+		<edge from-layer="18" from-port="8" to-layer="21" to-port="2" />
+		<edge from-layer="18" from-port="9" to-layer="21" to-port="3" />
+		<edge from-layer="19" from-port="0" to-layer="21" to-port="4" />
+		<edge from-layer="20" from-port="0" to-layer="21" to-port="5" />
+		<edge from-layer="21" from-port="6" to-layer="35" to-port="2" />
+		<edge from-layer="21" from-port="7" to-layer="35" to-port="3" />
+		<edge from-layer="21" from-port="8" to-layer="35" to-port="4" />
+		<edge from-layer="22" from-port="0" to-layer="35" to-port="5" />
+		<edge from-layer="23" from-port="0" to-layer="35" to-port="6" />
+		<edge from-layer="24" from-port="0" to-layer="35" to-port="7" />
+		<edge from-layer="25" from-port="0" to-layer="35" to-port="8" />
+		<edge from-layer="26" from-port="0" to-layer="35" to-port="9" />
+		<edge from-layer="27" from-port="0" to-layer="35" to-port="10" />
+		<edge from-layer="28" from-port="0" to-layer="35" to-port="11" />
+		<edge from-layer="29" from-port="0" to-layer="35" to-port="12" />
+		<edge from-layer="30" from-port="0" to-layer="35" to-port="13" />
+		<edge from-layer="31" from-port="0" to-layer="35" to-port="14" />
+		<edge from-layer="32" from-port="0" to-layer="35" to-port="15" />
+		<edge from-layer="33" from-port="0" to-layer="35" to-port="16" />
+		<edge from-layer="34" from-port="0" to-layer="35" to-port="17" />
+		<edge from-layer="35" from-port="18" to-layer="39" to-port="0" />
+		<edge from-layer="35" from-port="19" to-layer="39" to-port="1" />
+		<edge from-layer="35" from-port="20" to-layer="39" to-port="2" />
+		<edge from-layer="36" from-port="0" to-layer="39" to-port="3" />
+		<edge from-layer="37" from-port="0" to-layer="39" to-port="4" />
+		<edge from-layer="38" from-port="0" to-layer="39" to-port="5" />
+		<edge from-layer="39" from-port="6" to-layer="41" to-port="0" />
+		<edge from-layer="39" from-port="8" to-layer="41" to-port="2" />
+		<edge from-layer="39" from-port="7" to-layer="41" to-port="1" />
+		<edge from-layer="40" from-port="0" to-layer="41" to-port="3" />
+		<edge from-layer="41" from-port="5" to-layer="42" to-port="0" />
+		<edge from-layer="41" from-port="4" to-layer="42" to-port="1" />
+		<edge from-layer="41" from-port="4" to-layer="46" to-port="0" />
+		<edge from-layer="41" from-port="5" to-layer="46" to-port="1" />
+		<edge from-layer="41" from-port="6" to-layer="46" to-port="2" />
+		<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="46" to-port="3" />
+		<edge from-layer="45" from-port="0" to-layer="46" to-port="4" />
+		<edge from-layer="46" from-port="6" to-layer="47" to-port="0" />
+		<edge from-layer="46" from-port="5" to-layer="50" to-port="0" />
+		<edge from-layer="47" from-port="1" to-layer="48" to-port="0" />
+		<edge from-layer="48" from-port="1" to-layer="49" to-port="0" />
+		<edge from-layer="50" from-port="1" to-layer="51" to-port="0" />
+	</edges>
+	<rt_info>
+		<add_attention_mask value="True" />
+		<add_prefix_space />
+		<add_special_tokens value="True" />
+		<bos_token_id value="1" />
+		<chat_template value="{% for message in messages %}{% if message['role'] == 'system' %}{{'&lt;|system|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'user' %}{{'&lt;|user|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'assistant' %}{{'&lt;|assistant|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% else %}{{ eos_token }}{% endif %}" />
+		<clean_up_tokenization_spaces />
+		<detokenizer_input_type value="i64" />
+		<eos_token_id value="32000" />
+		<handle_special_tokens_with_re />
+		<max_length />
+		<number_of_inputs value="1" />
+		<openvino_tokenizers_version value="2025.2.0.0-566-85be884a69f" />
+		<openvino_version value="2025.2.0-19136-649eec15cfe-releases/2025/2" />
+		<original_post_processor_template value="{&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}], &quot;pair&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 1}}], &quot;special_tokens&quot;: {}}" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
+		<pad_token_id value="32000" />
+		<processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 1]}}" />
+		<sentencepiece_version value="0.2.0" />
+		<skip_special_tokens value="True" />
+		<streaming_detokenizer value="False" />
+		<tiktoken_version value="0.9.0" />
+		<tokenizer_output_type value="i64" />
+		<tokenizers_version value="0.21.1" />
+		<transformers_version value="4.51.3" />
+		<use_max_padding value="False" />
+		<use_sentencepiece_backend value="False" />
+		<utf8_replace_mode value="replace" />
+		<with_detokenizer value="True" />
+	</rt_info>
+</net>

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}