Delete int8_asym-ov

int8_asym-ov/added_tokens.json

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

int8_asym-ov/config.json

@@ -1,144 +0,0 @@
-{
-  "_attn_implementation_autoset": true,
-  "architectures": [
-    "Phi3ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "configuration_phi3.Phi3Config",
-    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
-    "AutoTokenizer": "Xenova/gpt-4o"
-  },
-  "bos_token_id": 199999,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 199999,
-  "full_attn_mod": 1,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "interpolate_factor": 1,
-  "lm_head_bias": false,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "phi3",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "original_max_position_embeddings": 4096,
-  "pad_token_id": 199999,
-  "partial_rotary_factor": 0.75,
-  "resid_pdrop": 0.0,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "long_factor": [
-      1,
-      1.118320672,
-      1.250641126,
-      1.398617824,
-      1.564103225,
-      1.74916897,
-      1.956131817,
-      2.187582649,
-      2.446418898,
-      2.735880826,
-      3.059592084,
-      3.421605075,
-      3.826451687,
-      4.279200023,
-      4.785517845,
-      5.351743533,
-      5.984965424,
-      6.693110555,
-      7.485043894,
-      8.370679318,
-      9.36110372,
-      10.4687158,
-      11.70738129,
-      13.09260651,
-      14.64173252,
-      16.37415215,
-      18.31155283,
-      20.47818807,
-      22.90118105,
-      25.61086418,
-      28.64115884,
-      32.03,
-      32.1,
-      32.13,
-      32.23,
-      32.6,
-      32.61,
-      32.64,
-      32.66,
-      32.7,
-      32.71,
-      32.93,
-      32.97,
-      33.28,
-      33.49,
-      33.5,
-      44.16,
-      47.77
-    ],
-    "short_factor": [
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0,
-      1.0
-    ],
-    "type": "longrope"
-  },
-  "rope_theta": 10000.0,
-  "sliding_window": 262144,
-  "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
-  "use_cache": true,
-  "vocab_size": 200064
-}

int8_asym-ov/configuration_phi3.py

@@ -1,226 +0,0 @@
-# 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__)
-
-
-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.
-        partial_rotary_factor (`float`, *optional*, defaults to 1.0):
-            Percentage of the query and keys which will have rotary embedding. Must be between 0.0 and 1.0.
-        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,
-        partial_rotary_factor=1.0,
-        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.partial_rotary_factor = partial_rotary_factor
-        self._rope_scaling_adjustment()
-        self._rope_scaling_validation()
-        self.sliding_window = sliding_window
-
-        super().__init__(
-            bos_token_id=bos_token_id,
-            eos_token_id=eos_token_id,
-            pad_token_id=pad_token_id,
-            tie_word_embeddings=tie_word_embeddings,
-            **kwargs,
-        )
-
-    def _rope_scaling_adjustment(self):
-        """
-        Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
-        """
-        if self.rope_scaling is None:
-            return
-
-        rope_scaling_type = self.rope_scaling.get("type", None)
-
-        # For backward compatibility if previous version used "su" or "yarn"
-        if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
-            self.rope_scaling["type"] = "longrope"
-
-    def _rope_scaling_validation(self):
-        """
-        Validate the `rope_scaling` configuration.
-        """
-        if self.rope_scaling is None:
-            return
-
-        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
-            raise ValueError(
-                "`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
-                f"got {self.rope_scaling}"
-            )
-        rope_scaling_type = self.rope_scaling.get("type", None)
-        rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
-        rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
-        if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
-            raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
-        if not (
-            isinstance(rope_scaling_short_factor, list)
-            and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
-        ):
-            raise ValueError(
-                f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
-            )
-        rotary_ndims = int(self.hidden_size // self.num_attention_heads * self.partial_rotary_factor)
-        if not len(rope_scaling_short_factor) == rotary_ndims // 2:
-            raise ValueError(
-                f"`rope_scaling`'s short_factor field must have length {rotary_ndims // 2}, got {len(rope_scaling_short_factor)}"
-            )
-        if not (
-            isinstance(rope_scaling_long_factor, list)
-            and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
-        ):
-            raise ValueError(
-                f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
-            )
-        if not len(rope_scaling_long_factor) == rotary_ndims // 2:
-            raise ValueError(
-                f"`rope_scaling`'s long_factor field must have length {rotary_ndims // 2}, got {len(rope_scaling_long_factor)}"
-            )

int8_asym-ov/generation_config.json

@@ -1,10 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 199999,
-  "eos_token_id": [
-    200020,
-    199999
-  ],
-  "pad_token_id": 199999,
-  "transformers_version": "4.51.3"
-}

int8_asym-ov/openvino_detokenizer.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:58ec20da66d1d780b298f3cdcf252ccc0e228636fc7bee219163af81f1837e0a
-size 2998349

int8_asym-ov/openvino_detokenizer.xml

@@ -1,219 +0,0 @@
-<?xml version="1.0"?>
-<net name="detokenizer" version="11">
-	<layers>
-		<layer id="0" name="Parameter_170636" type="Parameter" version="opset1">
-			<data shape="?,?" element_type="i64" />
-			<output>
-				<port id="0" precision="I64" names="Parameter_170636">
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="1" name="Convert_170806" 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_170638" type="Const" version="opset1">
-			<data element_type="i32" shape="200029" offset="0" size="800116" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>200029</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="3" name="Constant_170640" type="Const" version="opset1">
-			<data element_type="i32" shape="200029" offset="800116" size="800116" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>200029</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="4" name="Constant_170642" type="Const" version="opset1">
-			<data element_type="u8" shape="1398089" offset="1600232" size="1398089" />
-			<output>
-				<port id="0" precision="U8">
-					<dim>1398089</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="5" name="Slice_170647" type="Const" version="opset1">
-			<data element_type="i32" shape="7" offset="2998321" size="28" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>7</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="6" name="VocabDecoder_170649" type="VocabDecoder" version="extension">
-			<data skip_tokens="" />
-			<input>
-				<port id="0" precision="I32">
-					<dim>-1</dim>
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>200029</dim>
-				</port>
-				<port id="2" precision="I32">
-					<dim>200029</dim>
-				</port>
-				<port id="3" precision="U8">
-					<dim>1398089</dim>
-				</port>
-				<port id="4" precision="I32">
-					<dim>7</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_170650" 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_170651" 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_170652" 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_170653,string_output">
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="10" name="Result_170653" type="Result" version="opset1" output_names="Result_170653,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" />
-		<bos_token_id value="199999" />
-		<chat_template value="{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|tool|>' + message['tools'] + '&lt;|/tool|>' + '&lt;|end|>' }}{% else %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>' }}{% else %}{{ eos_token }}{% endif %}" />
-		<clean_up_tokenization_spaces />
-		<detokenizer_input_type value="i64" />
-		<eos_token_id value="199999" />
-		<handle_special_tokens_with_re />
-		<max_length />
-		<number_of_inputs value="1" />
-		<openvino_tokenizers_version value="2025.1.0.0-523-710ddf14de8" />
-		<openvino_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
-		<original_tokenizer_class value="&lt;class 'transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast'>" />
-		<pad_token_id value="199999" />
-		<sentencepiece_version value="0.2.0" />
-		<skip_special_tokens value="True" />
-		<streaming_detokenizer value="False" />
-		<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>

int8_asym-ov/openvino_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b889c2b0977e68d76017c9ad226081d1c9f30560173b57456ed78f142ecc6e2d
-size 3839875692

int8_asym-ov/openvino_tokenizer.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:818537d6633196e2f45e51017a6320010ca3c06120460c14028a6c325f92f477
-size 7602768

int8_asym-ov/openvino_tokenizer.xml

@@ -1,685 +0,0 @@
-<?xml version="1.0"?>
-<net name="tokenizer" version="11">
-	<layers>
-		<layer id="0" name="Parameter_170518" type="Parameter" version="opset1">
-			<data shape="?" element_type="string" />
-			<output>
-				<port id="0" precision="STRING" names="Parameter_170518">
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="1" name="Constant_170524" 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_170519" 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_170520" 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_170521" 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_170522" 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_170523" 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_170525" 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_170526" 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_170527" 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_170528" 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_170529" 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_170530" 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_170531" 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_170593" type="Const" version="opset1">
-			<data element_type="u8" shape="289" offset="16" size="289" />
-			<output>
-				<port id="0" precision="U8">
-					<dim>289</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="15" name="SpecialTokensSplit_170594" 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>289</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_170596" type="Const" version="opset1">
-			<data element_type="u8" shape="274" offset="305" size="274" />
-			<output>
-				<port id="0" precision="U8">
-					<dim>274</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="17" name="RegexSplit_170597" type="RegexSplit" version="extension">
-			<data behaviour="remove" invert="true" max_splits="-1" />
-			<input>
-				<port id="0" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="2" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="3" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="4" precision="U8">
-					<dim>-1</dim>
-				</port>
-				<port id="5" precision="BOOL">
-					<dim>-1</dim>
-				</port>
-				<port id="6" precision="U8">
-					<dim>274</dim>
-				</port>
-			</input>
-			<output>
-				<port id="7" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="8" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="9" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="10" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="11" precision="U8">
-					<dim>-1</dim>
-				</port>
-				<port id="12" precision="BOOL">
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="18" name="Constant_170599" type="Const" version="opset1">
-			<data element_type="i32" shape="200029" offset="579" size="800116" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>200029</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="19" name="Constant_170601" type="Const" version="opset1">
-			<data element_type="i32" shape="200029" offset="800695" size="800116" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>200029</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="20" name="Constant_170603" type="Const" version="opset1">
-			<data element_type="u8" shape="1398109" offset="1600811" size="1398109" />
-			<output>
-				<port id="0" precision="U8">
-					<dim>1398109</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="21" name="Constant_170611" type="Const" version="opset1">
-			<data element_type="i32" shape="199742" offset="2998920" size="798968" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>199742</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="22" name="Constant_170613" type="Const" version="opset1">
-			<data element_type="i32" shape="199742" offset="3797888" size="798968" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>199742</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="23" name="Constant_170615" type="Const" version="opset1">
-			<data element_type="u8" shape="718313" offset="4596856" size="718313" />
-			<output>
-				<port id="0" precision="U8">
-					<dim>718313</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="24" name="Constant_170617" type="Const" version="opset1">
-			<data element_type="i32" shape="199742" offset="5315169" size="798968" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>199742</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="25" name="Constant_170619" type="Const" version="opset1">
-			<data element_type="i32" shape="199742" offset="6114137" size="798968" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>199742</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="26" name="Constant_170621" type="Const" version="opset1">
-			<data element_type="u8" shape="679101" offset="6913105" size="679101" />
-			<output>
-				<port id="0" precision="U8">
-					<dim>679101</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="27" name="Constant_170605" type="Const" version="opset1">
-			<data element_type="i32" shape="432" offset="7592206" size="1728" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>432</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="28" name="Constant_170607" type="Const" version="opset1">
-			<data element_type="i32" shape="432" offset="7593934" size="1728" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>432</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="29" name="Constant_170609" type="Const" version="opset1">
-			<data element_type="u8" shape="5366" offset="7595662" size="5366" />
-			<output>
-				<port id="0" precision="U8">
-					<dim>5366</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="30" name="Constant_170622" type="Const" version="opset1">
-			<data element_type="i32" shape="432" offset="7601028" size="1728" />
-			<output>
-				<port id="0" precision="I32">
-					<dim>432</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="31" name="BPETokenizer_170623" type="BPETokenizer" version="extension">
-			<data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="40003" />
-			<input>
-				<port id="0" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="2" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="3" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="4" precision="U8">
-					<dim>-1</dim>
-				</port>
-				<port id="5" precision="I32">
-					<dim>200029</dim>
-				</port>
-				<port id="6" precision="I32">
-					<dim>200029</dim>
-				</port>
-				<port id="7" precision="U8">
-					<dim>1398109</dim>
-				</port>
-				<port id="8" precision="I32">
-					<dim>199742</dim>
-				</port>
-				<port id="9" precision="I32">
-					<dim>199742</dim>
-				</port>
-				<port id="10" precision="U8">
-					<dim>718313</dim>
-				</port>
-				<port id="11" precision="I32">
-					<dim>199742</dim>
-				</port>
-				<port id="12" precision="I32">
-					<dim>199742</dim>
-				</port>
-				<port id="13" precision="U8">
-					<dim>679101</dim>
-				</port>
-				<port id="14" precision="I32">
-					<dim>432</dim>
-				</port>
-				<port id="15" precision="I32">
-					<dim>432</dim>
-				</port>
-				<port id="16" precision="U8">
-					<dim>5366</dim>
-				</port>
-				<port id="17" precision="I32">
-					<dim>432</dim>
-				</port>
-			</input>
-			<output>
-				<port id="18" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="19" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="20" precision="I32">
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="32" name="Subtract_170624" 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="33" name="Constant_170625" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="7602756" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="34" name="Minimum_170626" 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="35" name="Subtract_170627" 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="36" name="Subtract_170628" 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="Constant_170629" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="7602760" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="38" name="ReduceMax_170630" 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="39" name="Constant_170631" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="7602764" size="4" />
-			<output>
-				<port id="0" precision="I32" />
-			</output>
-		</layer>
-		<layer id="40" name="RaggedToDense_170632" 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="41" name="Convert_170633" 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="42" name="Convert_170633.0" 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="44" name="RaggedToDense_170632.0" 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="45" name="Result_170634" 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="43" name="Result_170635" 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="2" to-layer="15" to-port="3" />
-		<edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
-		<edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
-		<edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
-		<edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
-		<edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
-		<edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
-		<edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
-		<edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
-		<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
-		<edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
-		<edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
-		<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
-		<edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
-		<edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
-		<edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
-		<edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
-		<edge from-layer="15" from-port="6" to-layer="17" to-port="0" />
-		<edge from-layer="15" from-port="7" to-layer="17" to-port="1" />
-		<edge from-layer="15" from-port="8" to-layer="17" to-port="2" />
-		<edge from-layer="15" from-port="9" to-layer="17" to-port="3" />
-		<edge from-layer="15" from-port="10" to-layer="17" to-port="4" />
-		<edge from-layer="15" from-port="11" to-layer="17" to-port="5" />
-		<edge from-layer="16" from-port="0" to-layer="17" to-port="6" />
-		<edge from-layer="17" from-port="7" to-layer="31" to-port="0" />
-		<edge from-layer="17" from-port="8" to-layer="31" to-port="1" />
-		<edge from-layer="17" from-port="9" to-layer="31" to-port="2" />
-		<edge from-layer="17" from-port="10" to-layer="31" to-port="3" />
-		<edge from-layer="17" from-port="11" to-layer="31" to-port="4" />
-		<edge from-layer="18" from-port="0" to-layer="31" to-port="5" />
-		<edge from-layer="19" from-port="0" to-layer="31" to-port="6" />
-		<edge from-layer="20" from-port="0" to-layer="31" to-port="7" />
-		<edge from-layer="21" from-port="0" to-layer="31" to-port="8" />
-		<edge from-layer="22" from-port="0" to-layer="31" to-port="9" />
-		<edge from-layer="23" from-port="0" to-layer="31" to-port="10" />
-		<edge from-layer="24" from-port="0" to-layer="31" to-port="11" />
-		<edge from-layer="25" from-port="0" to-layer="31" to-port="12" />
-		<edge from-layer="26" from-port="0" to-layer="31" to-port="13" />
-		<edge from-layer="27" from-port="0" to-layer="31" to-port="14" />
-		<edge from-layer="28" from-port="0" to-layer="31" to-port="15" />
-		<edge from-layer="29" from-port="0" to-layer="31" to-port="16" />
-		<edge from-layer="30" from-port="0" to-layer="31" to-port="17" />
-		<edge from-layer="31" from-port="19" to-layer="35" to-port="0" />
-		<edge from-layer="31" from-port="20" to-layer="40" to-port="2" />
-		<edge from-layer="31" from-port="19" to-layer="40" to-port="1" />
-		<edge from-layer="31" from-port="19" to-layer="36" to-port="0" />
-		<edge from-layer="31" from-port="18" to-layer="32" to-port="1" />
-		<edge from-layer="31" from-port="19" to-layer="32" to-port="0" />
-		<edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
-		<edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
-		<edge from-layer="34" from-port="2" to-layer="35" to-port="1" />
-		<edge from-layer="35" from-port="2" to-layer="36" to-port="1" />
-		<edge from-layer="35" from-port="2" to-layer="40" to-port="0" />
-		<edge from-layer="36" from-port="2" to-layer="38" to-port="0" />
-		<edge from-layer="37" from-port="0" to-layer="38" to-port="1" />
-		<edge from-layer="38" from-port="2" to-layer="40" to-port="3" />
-		<edge from-layer="39" from-port="0" to-layer="40" to-port="4" />
-		<edge from-layer="40" from-port="6" to-layer="41" to-port="0" />
-		<edge from-layer="40" from-port="5" to-layer="44" to-port="0" />
-		<edge from-layer="41" from-port="1" to-layer="42" to-port="0" />
-		<edge from-layer="42" from-port="1" to-layer="43" to-port="0" />
-		<edge from-layer="44" from-port="1" to-layer="45" to-port="0" />
-	</edges>
-	<rt_info>
-		<add_attention_mask value="True" />
-		<add_prefix_space />
-		<add_special_tokens value="True" />
-		<bos_token_id value="199999" />
-		<chat_template value="{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|tool|>' + message['tools'] + '&lt;|/tool|>' + '&lt;|end|>' }}{% else %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>' }}{% else %}{{ eos_token }}{% endif %}" />
-		<clean_up_tokenization_spaces />
-		<detokenizer_input_type value="i64" />
-		<eos_token_id value="199999" />
-		<handle_special_tokens_with_re />
-		<max_length />
-		<number_of_inputs value="1" />
-		<openvino_tokenizers_version value="2025.1.0.0-523-710ddf14de8" />
-		<openvino_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
-		<original_tokenizer_class value="&lt;class 'transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast'>" />
-		<pad_token_id value="199999" />
-		<sentencepiece_version value="0.2.0" />
-		<skip_special_tokens value="True" />
-		<streaming_detokenizer value="False" />
-		<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>

int8_asym-ov/special_tokens_map.json

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

int8_asym-ov/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
-size 15524095

int8_asym-ov/tokenizer_config.json

@@ -1,112 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_eos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "199999": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200018": {
-      "content": "<|endofprompt|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "200019": {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "200020": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "200021": {
-      "content": "<|user|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "200022": {
-      "content": "<|system|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "200023": {
-      "content": "<|tool|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "200024": {
-      "content": "<|/tool|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "200025": {
-      "content": "<|tool_call|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "200026": {
-      "content": "<|/tool_call|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "200027": {
-      "content": "<|tool_response|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "200028": {
-      "content": "<|tag|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|endoftext|>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "extra_special_tokens": {},
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
-}