Upload folder using huggingface_hub

.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

README.md

@@ -0,0 +1,105 @@
+---
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2-1.5B/blob/main/LICENSE
+base_model: 
+  - Qwen/Qwen2-1.5B
+base_model_relation: quantized
+
+---
+# Qwen2-1.5B-int8-ov
+ * Model creator: [Qwen](https://huggingface.co/Qwen)
+ * Original model: [Qwen2-1.5B](https://huggingface.co/Qwen/Qwen2-1.5B)
+
+## Description
+This is [Qwen2-1.5B](https://huggingface.co/Qwen/Qwen2-1.5B) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2025/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT8 by [NNCF](https://github.com/openvinotoolkit/nncf).
+
+## Quantization Parameters
+
+Weight compression was performed using `nncf.compress_weights` with the following parameters:
+
+* mode: **INT8_ASYM**
+
+For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2025/openvino-workflow/model-optimization-guide/weight-compression.html).
+
+## Compatibility
+
+The provided OpenVINO™ IR model is compatible with:
+
+* OpenVINO version 2025.1.0 and higher
+* Optimum Intel 1.24.0 and higher
+
+## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)
+
+1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
+
+```
+pip install optimum[openvino]
+```
+
+2. Run model inference:
+
+```
+from transformers import AutoTokenizer
+from optimum.intel.openvino import OVModelForCausalLM
+
+model_id = "OpenVINO/qwen2-1.5b-int8-ov"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = OVModelForCausalLM.from_pretrained(model_id)
+
+inputs = tokenizer("What is OpenVINO?", return_tensors="pt")
+
+outputs = model.generate(**inputs, max_length=200)
+text = tokenizer.batch_decode(outputs)[0]
+print(text)
+```
+
+For more examples and possible optimizations, refer to the [Inference with Optimum Intel](https://docs.openvino.ai/2025/openvino-workflow-generative/inference-with-optimum-intel.html).
+
+## 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/qwen2-1.5b-int8-ov"
+model_path = "qwen2-1.5b-int8-ov"
+
+hf_hub.snapshot_download(model_id, local_dir=model_path)
+
+```
+
+3. Run model inference:
+
+```
+import openvino_genai as ov_genai
+
+device = "CPU"
+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://docs.openvino.ai/2025/openvino-workflow-generative/inference-with-genai.html) and [samples](https://github.com/openvinotoolkit/openvino.genai?tab=readme-ov-file#openvino-genai-samples)
+
+You can find more detaild usage examples in OpenVINO Notebooks:
+
+- [LLM](https://openvinotoolkit.github.io/openvino_notebooks/?search=LLM)
+- [RAG text generation](https://openvinotoolkit.github.io/openvino_notebooks/?search=RAG+system&tasks=Text+Generation)
+
+## Limitations
+
+Check the original [model card](https://huggingface.co/Qwen/Qwen2-1.5B) for limitations.
+
+## Legal information
+
+The original model is distributed under [Apache License Version 2.0](https://huggingface.co/Qwen/Qwen2-1.5B/blob/main/LICENSE) license. More details can be found in [Qwen2-1.5B](https://huggingface.co/Qwen/Qwen2-1.5B).
+
+## 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 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

openvino_detokenizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0f3c523b66659e393c0977a685899206c3d419c5a8138e45ba44d69cb40ba1
+size 2189184

openvino_detokenizer.xml

@@ -0,0 +1,220 @@
+<?xml version="1.0"?>
+<net name="detokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_83136" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="Parameter_83136">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Convert_83306" 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_83138" type="Const" version="opset1">
+			<data element_type="i32" shape="151646" offset="0" size="606584" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151646</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Constant_83140" type="Const" version="opset1">
+			<data element_type="i32" shape="151646" offset="606584" size="606584" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151646</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_83142" type="Const" version="opset1">
+			<data element_type="u8" shape="976004" offset="1213168" size="976004" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>976004</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="Slice_83147" type="Const" version="opset1">
+			<data element_type="i32" shape="3" offset="2189172" size="12" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="VocabDecoder_83149" 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>151646</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>151646</dim>
+				</port>
+				<port id="3" precision="U8">
+					<dim>976004</dim>
+				</port>
+				<port id="4" precision="I32">
+					<dim>3</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_83150" 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_83151" 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_83152" 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_83153,string_output">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="Result_83153" type="Result" version="opset1" output_names="Result_83153,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="7" to-layer="7" to-port="2" />
+		<edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
+		<edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
+		<edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
+		<edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
+		<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" />
+		<chat_template value="{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '&lt;|im_start|>system&#10;You are a helpful assistant&lt;|im_end|>&#10;' }}{% endif %}{{'&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;'}}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
+		<clean_up_tokenization_spaces />
+		<detokenizer_input_type value="i64" />
+		<eos_token_id value="151643" />
+		<handle_special_tokens_with_re />
+		<max_length />
+		<number_of_inputs value="1" />
+		<openvino_tokenizers_version value="2025.1.0.0-523-710ddf14de8" />
+		<openvino_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
+		<original_post_processor_template value="{&quot;type&quot;: &quot;ByteLevel&quot;, &quot;add_prefix_space&quot;: false, &quot;trim_offsets&quot;: false, &quot;use_regex&quot;: false}" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
+		<pad_token_id value="151643" />
+		<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:ecd49d6acfb32dbaae2b9c1fc14d91974d78805b1d416d1e64cb695ac57e4293
+size 1546426004

openvino_tokenizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1770093b00540d509d2790ad81bfce38e49e110b06b58b06611c3ae4093b53b
+size 5587341

openvino_tokenizer.xml

@@ -0,0 +1,721 @@
+<?xml version="1.0"?>
+<net name="tokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_83017" type="Parameter" version="opset1">
+			<data shape="?" element_type="string" />
+			<output>
+				<port id="0" precision="STRING" names="Parameter_83017">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Constant_83023" 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_83018" 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_83019" 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_83020" 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_83021" 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_83022" 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_83024" 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_83025" 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_83026" 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_83027" 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_83028" 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_83029" 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_83030" 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_83092" type="Const" version="opset1">
+			<data element_type="u8" shape="55" offset="16" size="55" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>55</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="SpecialTokensSplit_83093" 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>55</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="CharsMapNormalization_83094" type="CharsMapNormalization" version="extension">
+			<data add_dummy_prefix="false" remove_extra_whitespaces="false" escape_whitespaces="false" normalization_form="nfc" case_fold="false" nmt="false" />
+			<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>
+			</input>
+			<output>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="Constant_83096" type="Const" version="opset1">
+			<data element_type="u8" shape="110" offset="71" size="110" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>110</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="RegexSplit_83097" type="RegexSplit" version="extension">
+			<data behaviour="isolate" invert="false" 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>110</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="19" name="Constant_83099" type="Const" version="opset1">
+			<data element_type="i32" shape="151646" offset="181" size="606584" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151646</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="Constant_83101" type="Const" version="opset1">
+			<data element_type="i32" shape="151646" offset="606765" size="606584" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151646</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="Constant_83103" type="Const" version="opset1">
+			<data element_type="u8" shape="976004" offset="1213349" size="976004" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>976004</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="Constant_83111" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="2189353" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="23" name="Constant_83113" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="2794901" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="24" name="Constant_83115" type="Const" version="opset1">
+			<data element_type="u8" shape="491359" offset="3400449" size="491359" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>491359</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="Constant_83117" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="3891808" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="26" name="Constant_83119" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="4497356" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="27" name="Constant_83121" type="Const" version="opset1">
+			<data element_type="u8" shape="484354" offset="5102904" size="484354" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>484354</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="28" name="Constant_83105" type="Const" version="opset1">
+			<data element_type="i32" shape="3" offset="5587258" size="12" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="29" name="Constant_83107" type="Const" version="opset1">
+			<data element_type="i32" shape="3" offset="5587270" size="12" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="30" name="Constant_83109" type="Const" version="opset1">
+			<data element_type="u8" shape="35" offset="5587282" size="35" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>35</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="31" name="Constant_83122" type="Const" version="opset1">
+			<data element_type="i32" shape="3" offset="5587317" size="12" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="32" name="BPETokenizer_83123" type="BPETokenizer" version="extension">
+			<data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="30328" />
+			<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>151646</dim>
+				</port>
+				<port id="6" precision="I32">
+					<dim>151646</dim>
+				</port>
+				<port id="7" precision="U8">
+					<dim>976004</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="10" precision="U8">
+					<dim>491359</dim>
+				</port>
+				<port id="11" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="12" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="13" precision="U8">
+					<dim>484354</dim>
+				</port>
+				<port id="14" precision="I32">
+					<dim>3</dim>
+				</port>
+				<port id="15" precision="I32">
+					<dim>3</dim>
+				</port>
+				<port id="16" precision="U8">
+					<dim>35</dim>
+				</port>
+				<port id="17" precision="I32">
+					<dim>3</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="33" name="Subtract_83124" 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="34" name="Constant_83125" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="5587329" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="35" name="Minimum_83126" type="Minimum" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32" />
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="36" name="Subtract_83127" 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="37" name="Subtract_83128" 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="38" name="Constant_83129" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="5587333" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="39" name="ReduceMax_83130" 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="40" name="Constant_83131" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="5587337" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="41" name="RaggedToDense_83132" 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="42" name="Convert_83133" 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="43" name="Convert_83133.0" 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="45" name="RaggedToDense_83132.0" 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="46" name="Result_83134" 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="44" name="Result_83135" 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="8" to-layer="16" to-port="0" />
+		<edge from-layer="15" from-port="7" to-layer="18" to-port="1" />
+		<edge from-layer="15" from-port="6" to-layer="18" to-port="0" />
+		<edge from-layer="15" from-port="11" to-layer="16" to-port="3" />
+		<edge from-layer="15" from-port="10" to-layer="16" to-port="2" />
+		<edge from-layer="15" from-port="9" to-layer="16" to-port="1" />
+		<edge from-layer="16" from-port="4" to-layer="18" to-port="2" />
+		<edge from-layer="16" from-port="5" to-layer="18" to-port="3" />
+		<edge from-layer="16" from-port="6" to-layer="18" to-port="4" />
+		<edge from-layer="16" from-port="7" to-layer="18" to-port="5" />
+		<edge from-layer="17" from-port="0" to-layer="18" to-port="6" />
+		<edge from-layer="18" from-port="11" to-layer="32" to-port="4" />
+		<edge from-layer="18" from-port="10" to-layer="32" to-port="3" />
+		<edge from-layer="18" from-port="8" to-layer="32" to-port="1" />
+		<edge from-layer="18" from-port="7" to-layer="32" to-port="0" />
+		<edge from-layer="18" from-port="9" to-layer="32" to-port="2" />
+		<edge from-layer="19" from-port="0" to-layer="32" to-port="5" />
+		<edge from-layer="20" from-port="0" to-layer="32" to-port="6" />
+		<edge from-layer="21" from-port="0" to-layer="32" to-port="7" />
+		<edge from-layer="22" from-port="0" to-layer="32" to-port="8" />
+		<edge from-layer="23" from-port="0" to-layer="32" to-port="9" />
+		<edge from-layer="24" from-port="0" to-layer="32" to-port="10" />
+		<edge from-layer="25" from-port="0" to-layer="32" to-port="11" />
+		<edge from-layer="26" from-port="0" to-layer="32" to-port="12" />
+		<edge from-layer="27" from-port="0" to-layer="32" to-port="13" />
+		<edge from-layer="28" from-port="0" to-layer="32" to-port="14" />
+		<edge from-layer="29" from-port="0" to-layer="32" to-port="15" />
+		<edge from-layer="30" from-port="0" to-layer="32" to-port="16" />
+		<edge from-layer="31" from-port="0" to-layer="32" to-port="17" />
+		<edge from-layer="32" from-port="19" to-layer="33" to-port="0" />
+		<edge from-layer="32" from-port="18" to-layer="33" to-port="1" />
+		<edge from-layer="32" from-port="20" to-layer="41" to-port="2" />
+		<edge from-layer="32" from-port="19" to-layer="36" to-port="0" />
+		<edge from-layer="32" from-port="19" to-layer="41" to-port="1" />
+		<edge from-layer="32" from-port="19" to-layer="37" to-port="0" />
+		<edge from-layer="33" from-port="2" to-layer="35" to-port="0" />
+		<edge from-layer="34" from-port="0" to-layer="35" to-port="1" />
+		<edge from-layer="35" from-port="2" to-layer="36" to-port="1" />
+		<edge from-layer="36" from-port="2" to-layer="37" to-port="1" />
+		<edge from-layer="36" from-port="2" to-layer="41" to-port="0" />
+		<edge from-layer="37" from-port="2" to-layer="39" to-port="0" />
+		<edge from-layer="38" from-port="0" to-layer="39" to-port="1" />
+		<edge from-layer="39" from-port="2" to-layer="41" to-port="3" />
+		<edge from-layer="40" from-port="0" to-layer="41" to-port="4" />
+		<edge from-layer="41" from-port="6" to-layer="42" to-port="0" />
+		<edge from-layer="41" from-port="5" to-layer="45" to-port="0" />
+		<edge from-layer="42" from-port="1" to-layer="43" to-port="0" />
+		<edge from-layer="43" from-port="1" to-layer="44" to-port="0" />
+		<edge from-layer="45" from-port="1" to-layer="46" to-port="0" />
+	</edges>
+	<rt_info>
+		<add_attention_mask value="True" />
+		<add_prefix_space />
+		<add_special_tokens value="True" />
+		<chat_template value="{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '&lt;|im_start|>system&#10;You are a helpful assistant&lt;|im_end|>&#10;' }}{% endif %}{{'&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;'}}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
+		<clean_up_tokenization_spaces />
+		<detokenizer_input_type value="i64" />
+		<eos_token_id value="151643" />
+		<handle_special_tokens_with_re />
+		<max_length />
+		<number_of_inputs value="1" />
+		<openvino_tokenizers_version value="2025.1.0.0-523-710ddf14de8" />
+		<openvino_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
+		<original_post_processor_template value="{&quot;type&quot;: &quot;ByteLevel&quot;, &quot;add_prefix_space&quot;: false, &quot;trim_offsets&quot;: false, &quot;use_regex&quot;: false}" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
+		<pad_token_id value="151643" />
+		<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 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}