Upload folder using huggingface_hub

config.json

@@ -0,0 +1,270 @@
+{
+  "architectures": [
+    "Ovis"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_ovis.OvisConfig",
+    "AutoModelForCausalLM": "modeling_ovis.Ovis"
+  },
+  "conversation_formatter_class": "Llama3ConversationFormatter",
+  "disable_tie_weight": false,
+  "hidden_size": 3072,
+  "llm_attn_implementation": "eager",
+  "llm_config": {
+    "_name_or_path": "meta-llama/Llama-3.2-3B",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 128000,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": [
+      128001,
+      128008,
+      128009
+    ],
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 131072,
+    "min_length": 0,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 24,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 32.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": false,
+    "vocab_size": 128256
+  },
+  "model_type": "ovis",
+  "multimodal_max_length": 2624,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "damp_percent": 0.1,
+    "desc_act": false,
+    "group_size": 128,
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "visual_tokenizer_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "SiglipVisualTokenizer"
+    ],
+    "backbone_config": {
+      "_name_or_path": "google/siglip-so400m-patch14-384",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_size": 1152,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 384,
+      "intermediate_size": 4304,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "siglip_vision_model",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_channels": 3,
+      "num_hidden_layers": 27,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "backbone_kwargs": {},
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_cls_token": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_stride": 2,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "siglip_visual_tokenizer",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "tau": 1.0,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenize_function": "softmax",
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_indicators": false,
+    "vocab_size": 65536
+  }
+}

configuration_ovis.py

@@ -0,0 +1,204 @@
+from abc import ABC, abstractmethod
+from typing import List, Dict, Union, Optional
+
+from transformers import PretrainedConfig, AutoConfig
+
+IGNORE_ID = -100
+IMAGE_TOKEN_ID = -200
+IMAGE_TOKEN = "<image>"
+IMAGE_ATOM_ID = -300
+IMAGE_INDICATOR_IDS = [-301, -302, -303, -304, -305]
+
+
+# ----------------------------------------------------------------------
+#                     Visual Tokenizer Configuration
+# ----------------------------------------------------------------------
+class BaseVisualTokenizerConfig(PretrainedConfig):
+    def __init__(
+        self,
+        vocab_size=16384,
+        tokenize_function="softmax",
+        tau=1.0,
+        depths=None,
+        drop_cls_token=False,
+        backbone_config: Optional[Union[PretrainedConfig, dict]] = None,
+        hidden_stride: int = 1,
+        **kwargs
+    ):
+        super().__init__(**kwargs)
+        self.vocab_size = vocab_size
+        self.tokenize_function = tokenize_function
+        self.tau = tau
+        if isinstance(depths, str):
+            depths = [int(x) for x in depths.split('|')]
+        self.depths = depths
+        self.backbone_kwargs = {}
+        self.drop_cls_token = drop_cls_token
+        if backbone_config is not None:
+            assert isinstance(backbone_config, (PretrainedConfig, dict)), \
+                f"expect `backbone_config` to be instance of PretrainedConfig or dict, but got {type(backbone_config)} type"
+            if not isinstance(backbone_config, PretrainedConfig):
+                model_type = backbone_config['model_type']
+                backbone_config.pop('model_type')
+                backbone_config = AutoConfig.for_model(model_type, **backbone_config)
+        self.backbone_config = backbone_config
+        self.hidden_stride = hidden_stride
+
+
+class SiglipVisualTokenizerConfig(BaseVisualTokenizerConfig):
+    model_type = "siglip_visual_tokenizer"
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        if self.drop_cls_token:
+            self.drop_cls_token = False
+        if self.depths:
+            assert len(self.depths) == 1
+            self.backbone_kwargs['num_hidden_layers'] = self.depths[0]
+
+
+AutoConfig.register("siglip_visual_tokenizer", SiglipVisualTokenizerConfig)
+
+
+# ----------------------------------------------------------------------
+#                           Ovis Configuration
+# ----------------------------------------------------------------------
+class OvisConfig(PretrainedConfig):
+    model_type = "ovis"
+
+    def __init__(
+        self,
+        llm_config: Optional[Union[PretrainedConfig, dict]] = None,
+        visual_tokenizer_config: Optional[Union[PretrainedConfig, dict]] = None,
+        multimodal_max_length=8192,
+        hidden_size=None,
+        conversation_formatter_class=None,
+        llm_attn_implementation=None,
+        disable_tie_weight=False,
+        **kwargs
+    ):
+        super().__init__(**kwargs)
+        if llm_config is not None:
+            assert isinstance(llm_config, (PretrainedConfig, dict)), \
+                f"expect `llm_config` to be instance of PretrainedConfig or dict, but got {type(llm_config)} type"
+            if not isinstance(llm_config, PretrainedConfig):
+                model_type = llm_config['model_type']
+                llm_config.pop('model_type')
+                llm_config = AutoConfig.for_model(model_type, **llm_config)
+        self.llm_config = llm_config
+        if visual_tokenizer_config is not None:
+            assert isinstance(visual_tokenizer_config, (PretrainedConfig, dict)), \
+                f"expect `visual_tokenizer_config` to be instance of PretrainedConfig or dict, but got {type(visual_tokenizer_config)} type"
+            if not isinstance(visual_tokenizer_config, PretrainedConfig):
+                model_type = visual_tokenizer_config['model_type']
+                visual_tokenizer_config.pop('model_type')
+                visual_tokenizer_config = AutoConfig.for_model(model_type, **visual_tokenizer_config)
+        self.visual_tokenizer_config = visual_tokenizer_config
+        self.multimodal_max_length = multimodal_max_length
+        self.hidden_size = hidden_size
+        self.conversation_formatter_class = conversation_formatter_class
+        self.llm_attn_implementation = llm_attn_implementation
+        self.disable_tie_weight = disable_tie_weight
+
+
+# ----------------------------------------------------------------------
+#                         Conversation Formatter
+# ----------------------------------------------------------------------
+class ConversationFormatter(ABC):
+    support_tokenizer_types = None
+
+    def __init__(self, tokenizer):
+        tokenizer_type = type(tokenizer).__name__
+        assert tokenizer_type in self.support_tokenizer_types, \
+            f'Invalid tokenizer type, expected one from `{self.support_tokenizer_types}`, but got `{tokenizer_type}`'
+        self.tokenizer = tokenizer
+        self.image_token = IMAGE_TOKEN
+        self.image_token_id = IMAGE_TOKEN_ID
+        self.ignore_id = IGNORE_ID
+
+    def _tokenize_with_image_symbol(self, text):
+        text_chunks = [self.tokenizer(chunk, add_special_tokens=False).input_ids for chunk in
+                       text.split(self.image_token)]
+        token_ids = []
+        num_chuck = len(text_chunks)
+        for i, chunk in enumerate(text_chunks):
+            token_ids.extend(chunk)
+            if i < num_chuck - 1:
+                token_ids.append(self.image_token_id)
+        return token_ids
+
+    @abstractmethod
+    def format(self, conversations: List[Dict], generation_preface=None):
+        pass
+
+    @abstractmethod
+    def format_query(self, query, generation_preface=""):
+        pass
+
+
+class Llama3ConversationFormatter(ConversationFormatter):
+    support_tokenizer_types = ['PreTrainedTokenizerFast']
+
+    def __init__(self, tokenizer):
+        super().__init__(tokenizer)
+        self.from2role = {
+            "system": "<|start_header_id|>system<|end_header_id|>\n\n",
+            "human": "<|start_header_id|>user<|end_header_id|>\n\n",
+            "gpt": "<|start_header_id|>assistant<|end_header_id|>\n\n",
+        }
+        self.gpt_token_num = None
+        self.im_end = "<|eot_id|>"
+        self.default_system_prompt = "You are a helpful and honest multimodal assistant."
+        self.bos_token = "<|begin_of_text|>"
+        self.bos_token_ids = None
+
+    def format(self, conversations: List[Dict], generation_preface=None):
+        if self.gpt_token_num is None:
+            self.gpt_token_num = len(self.tokenizer(self.from2role["gpt"], add_special_tokens=False).input_ids)
+
+        if self.bos_token_ids is None:
+            self.bos_token_ids = self.tokenizer(self.bos_token, add_special_tokens=False).input_ids
+
+        if conversations[0]["from"] != "system":
+            conversations.insert(0, {
+                "from": "system",
+                "value": self.default_system_prompt
+            })
+
+        if generation_preface is not None:
+            conversations.append({
+                "from": "gpt",
+                "value": generation_preface
+            })
+
+        prompt = "" + self.bos_token
+        input_ids = [] + self.bos_token_ids
+        labels = [] + [IGNORE_ID] * len(input_ids)
+        num_conversation = len(conversations)
+        for i, conversation in enumerate(conversations):
+            frm = conversation["from"]
+            role = self.from2role[frm]
+            message = conversation["value"].strip()
+            text = role + message
+            if i < num_conversation - 1 or generation_preface is None:
+                text += self.im_end
+            prompt += text
+            token_ids = self._tokenize_with_image_symbol(text)
+            input_ids.extend(token_ids)
+            label_ids = [self.ignore_id] * len(token_ids)
+            if frm == "gpt":
+                label_ids[self.gpt_token_num:] = token_ids[self.gpt_token_num:]
+            labels.extend(label_ids)
+
+        assert self._tokenize_with_image_symbol(prompt) == input_ids
+        assert len(input_ids) == len(labels)
+
+        return prompt, input_ids, labels
+
+    def format_query(self, query, generation_preface=""):
+        prompt, input_ids, _ = self.format([{
+            "from": "human",
+            "value": query
+        }], generation_preface=generation_preface)
+
+        return prompt, input_ids

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "multimodal_max_length": 2624,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7634723adac5657effbd03138485dd3f7a16cac82b5b9840edfe5d47d2353ad0
+size 4907144020

modeling_ovis.py

@@ -0,0 +1,601 @@
+import logging
+import os
+from importlib import import_module
+from typing import List, Callable, Union, Optional, Dict
+
+import PIL.Image
+import torch
+from torch import Tensor
+from torch.nn import init
+from torch.nn.functional import softmax, gumbel_softmax, pad
+from transformers import PreTrainedModel, AutoModel, AutoTokenizer, AutoModelForCausalLM, AutoImageProcessor
+from transformers import SiglipImageProcessor, SiglipVisionModel
+from transformers.cache_utils import HybridCache
+from transformers.generation.utils import GenerateOutput
+
+from .configuration_ovis import BaseVisualTokenizerConfig, SiglipVisualTokenizerConfig
+from .configuration_ovis import OvisConfig, ConversationFormatter
+from .configuration_ovis import IGNORE_ID, IMAGE_ATOM_ID, IMAGE_INDICATOR_IDS, IMAGE_TOKEN_ID
+
+
+# ----------------------------------------------------------------------
+#                            Visual Tokenizer
+# ----------------------------------------------------------------------
+class BaseVisualTokenizer(PreTrainedModel):
+    base_model_prefix = "backbone"
+    main_input_name = None
+    _image_processor_class = None
+    _image_processor_kwargs = {}
+    _backbone_class = None
+    _backbone_name_or_path = None
+
+    def __init__(self, config: BaseVisualTokenizerConfig, *inputs, **kwargs):
+        super().__init__(config, *inputs, **kwargs)
+        self.image_processor = AutoImageProcessor.from_pretrained(kwargs['image_processor_name_or_path'])
+        self.backbone = AutoModel.from_config(self.config.backbone_config)
+        head_dim = self.config.vocab_size - len(IMAGE_INDICATOR_IDS)  # reserved tokens for IMAGE_INDICATORS
+        self.head = torch.nn.Sequential(
+            torch.nn.Linear(
+                self.backbone.config.hidden_size * self.config.hidden_stride * self.config.hidden_stride, head_dim,
+                bias=False
+            ),
+            torch.nn.LayerNorm(head_dim)
+        )
+
+        assert all((self.image_processor.do_resize,
+                    not getattr(self.image_processor, 'do_center_crop', False),
+                    self.image_processor.do_rescale,
+                    self.image_processor.do_normalize
+                    )), f"image_processor `{self.image_processor}` is not supported currently"
+
+    def get_backbone(self):
+        return self.backbone
+
+    def get_image_processor(self):
+        return self.image_processor
+
+    def mock_input(self):
+        height, width = self.get_image_size()
+        return torch.zeros(1, 3, height, width), self.construct_image_placeholders((1, 1))
+
+    def get_head(self):
+        return self.head
+
+    def get_image_size(self):
+        raise NotImplementedError
+
+    @staticmethod
+    def construct_image_placeholders(grid):
+        image_placeholders = [IMAGE_INDICATOR_IDS[0], IMAGE_ATOM_ID, IMAGE_INDICATOR_IDS[1]]
+        if grid[0] * grid[1] > 1:
+            for r in range(grid[0]):
+                for c in range(grid[1]):
+                    image_placeholders.append(IMAGE_ATOM_ID)
+                    if c < grid[1] - 1:
+                        image_placeholders.append(IMAGE_INDICATOR_IDS[2])
+                if r < grid[0] - 1:
+                    image_placeholders.append(IMAGE_INDICATOR_IDS[3])
+        image_placeholders.append(IMAGE_INDICATOR_IDS[4])
+        return image_placeholders
+
+    def preprocess_image(self, image: PIL.Image.Image, max_partition=9, covering_threshold=0.9, convert_to_rgb=True):
+        def _preprocess(img: PIL.Image.Image, side):
+            # first resize and preprocess
+            w, h = img.size
+            if w == h:
+                new_width = new_height = side
+            elif w > h:
+                new_width = side
+                new_height = int(h / w * new_width)
+            else:
+                new_height = side
+                new_width = int(w / h * new_height)
+            new_size = dict(height=new_height, width=new_width)
+            pixel_values = self.image_processor.preprocess(img, size=new_size, return_tensors='pt')['pixel_values']
+
+            # then pad to square
+            square_values = torch.zeros([1, 3, side, side], dtype=pixel_values.dtype, device=pixel_values.device)
+            new_height, new_width = pixel_values.shape[2:]
+            if new_height == new_width:
+                square_values[:, :, :, :] = pixel_values
+            elif new_height > new_width:
+                from_index = (side - new_width) // 2
+                square_values[:, :, :, from_index:from_index + new_width] = pixel_values
+            else:
+                from_index = (side - new_height) // 2
+                square_values[:, :, from_index:from_index + new_height, :] = pixel_values
+
+            return square_values
+
+        def _partition(img, grid):
+            w, h = img.size
+            row_height = h // grid[0]
+            col_width = w // grid[1]
+
+            partition = []
+            for row in range(grid[0]):
+                for col in range(grid[1]):
+                    left = col * col_width
+                    upper = row * row_height
+                    right = w if col == grid[1] - 1 else (col + 1) * col_width
+                    lower = h if row == grid[0] - 1 else (row + 1) * row_height
+                    partition.append((left, upper, right, lower))
+
+            return partition
+
+        def _covering_area(left, upper, right, lower, side):
+            w = right - left
+            h = lower - upper
+            w, h = max(w, h), min(w, h)
+            if w > side:
+                h = h / w * side
+                w = side
+            return w * h
+
+        def _get_best_grid(img, side):
+            img_area = img.size[0] * img.size[1]
+
+            candidate_grids = []
+            for i in range(1, max_partition + 1):
+                for j in range(1, max_partition + 1):
+                    if i * j <= max_partition:
+                        candidate_grids.append((i, j))
+
+            all_grids = []
+            good_grids = []
+            for grid in candidate_grids:
+                partition = _partition(img, grid)
+                covering_ratio = sum([_covering_area(*p, side) for p in partition]) / img_area
+                assert covering_ratio <= 1.0
+                all_grids.append((grid, covering_ratio))
+                if covering_ratio > covering_threshold:
+                    good_grids.append((grid, covering_ratio))
+
+            if len(good_grids) > 0:
+                # pick the good partition with minimum #sub_images and break the tie using covering_ratio
+                return sorted(good_grids, key=lambda x: (x[0][0] * x[0][1], -x[1]))[0][0]
+            else:
+                # pick the partition with maximum covering_ratio and break the tie using #sub_images
+                return sorted(all_grids, key=lambda x: (-x[1], x[0][0] * x[0][1]))[0][0]
+
+        if convert_to_rgb and image.mode != 'RGB':
+            image = image.convert('RGB')
+
+        sides = self.get_image_size()
+        if sides[0] != sides[1]:
+            raise ValueError('get_image_size() returns non-square size')
+        side = sides[0]
+        grid = _get_best_grid(image, side)
+        partition = _partition(image, grid)
+        crops = [image.crop(p) for p in partition]
+        if len(crops) > 1:
+            crops.insert(0, image)
+        pixel_values = torch.cat([_preprocess(crop, side) for crop in crops], dim=0)
+        image_placeholders = self.construct_image_placeholders(grid)
+        return pixel_values, image_placeholders
+
+    def tokenize(self, logits):
+        def st_argmax(y_soft, dim):  # straight-through softmax
+            index = y_soft.max(dim, keepdim=True)[1]
+            y_hard = torch.zeros_like(y_soft, memory_format=torch.legacy_contiguous_format).scatter_(dim, index, 1.0)
+            ret = y_hard - y_soft.detach() + y_soft
+            return ret
+
+        if self.config.tokenize_function == 'softmax':
+            tokens = softmax(logits, dim=-1)
+        elif self.config.tokenize_function == 'gumbel_argmax':
+            tokens = gumbel_softmax(logits, tau=self.config.tau, hard=True)
+        elif self.config.tokenize_function == 'st_argmax':
+            tokens = st_argmax(logits, dim=-1)
+        else:
+            raise ValueError(
+                f'Invalid `max_type`, expected softmax or gumbel_argmax or st_argmax, but got {self.config.tokenize_function}')
+        return tokens
+
+    def encode(self, pixel_values):
+        output = self.backbone(pixel_values, output_hidden_states=True, return_dict=True)
+        features = output.hidden_states[-1]
+        if self.config.drop_cls_token:
+            features = features[:, 1:, :]
+
+        # merge number of `hidden_stride * hidden_stride` hidden states together to reduce token sequence length
+        # e.g., for hidden_stride=3, this leads to a token length reduction: 729 -> 81 for siglip
+        if self.config.hidden_stride > 1:
+            n, l, d = features.shape  # this `d` maybe different from the above `d
+            sqrt_l = int(l ** 0.5)
+            assert sqrt_l ** 2 == l, "The token sequence length should be a perfect square."
+            features = features.reshape(n, sqrt_l, sqrt_l, d)
+            pl = (self.config.hidden_stride - (sqrt_l % self.config.hidden_stride)) % self.config.hidden_stride
+            features = pad(features, (0, 0, 0, pl, 0, pl), "constant", 0)
+            sqrt_l += pl
+            features = features.reshape(n, sqrt_l // self.config.hidden_stride, self.config.hidden_stride,
+                                        sqrt_l // self.config.hidden_stride, self.config.hidden_stride, d)
+            features = features.permute(0, 1, 3, 2, 4, 5)  # [n, sqrt_l/hs, sqrt_l/hs, hs, hs, d]
+            features = features.flatten(3)  # [n, sqrt_l/hs, sqrt_l/hs, hs*hs*d]
+            features = features.reshape(
+                n, -1, self.config.hidden_stride * self.config.hidden_stride * d)
+
+        return features
+
+    def forward(self, pixel_values) -> torch.Tensor:  # [BatchSize, ImageShape] -> [BatchSize, #Token, VocabSize]
+        features = self.encode(pixel_values)
+        logits = self.head(features)
+        tokens = self.tokenize(logits)
+        # tokens' shape is [BatchSize, #Token, VocabSize-5], so padding with [BatchSize, #Token, 5], after
+        # which, tokens' shape should become [BatchSize, #Token, VocabSize]
+        batch_size, token_len, _ = tokens.shape
+        padding_tensor = torch.zeros(size=(batch_size, token_len, len(IMAGE_INDICATOR_IDS)),
+                                     dtype=tokens.dtype,
+                                     device=tokens.device,
+                                     layout=tokens.layout,
+                                     requires_grad=False)
+        tokens = torch.cat((tokens, padding_tensor), dim=2)
+        return tokens
+
+
+class SiglipVisualTokenizer(BaseVisualTokenizer):
+    config_class = SiglipVisualTokenizerConfig
+    supports_gradient_checkpointing = True
+    _no_split_modules = ["SiglipVisionTransformer"]
+    _image_processor_class = SiglipImageProcessor
+    _image_processor_kwargs = {}
+    _backbone_class = SiglipVisionModel
+    _backbone_name_or_path = "google/siglip-so400m-patch14-384"
+
+    def get_image_size(self):
+        height = self.image_processor.size["height"]
+        width = self.image_processor.size["width"]
+        return height, width
+
+
+AutoModel.register(SiglipVisualTokenizerConfig, SiglipVisualTokenizer)
+
+
+# ----------------------------------------------------------------------
+#                                  Ovis
+# ----------------------------------------------------------------------
+class VisualEmbedding(torch.nn.Embedding):
+    def forward(self, visual_tokens: Tensor) -> Tensor:
+        if visual_tokens.dtype in [torch.int8, torch.int16, torch.int32, torch.int64, torch.long]:
+            return super().forward(visual_tokens)
+        return torch.matmul(visual_tokens, self.weight)
+
+    def reset_parameters(self, mean=0., std=1.) -> None:
+        init.normal_(self.weight, mean=mean, std=std)
+        self._fill_padding_idx_with_zero()
+
+
+class OvisPreTrainedModel(PreTrainedModel):
+    config_class = OvisConfig
+    base_model_prefix = "ovis"
+
+
+class Ovis(OvisPreTrainedModel):
+
+    def __init__(self, config: OvisConfig, *inputs, **kwargs):
+        super().__init__(config, *inputs, **kwargs)
+        attn_kwargs = dict()
+        if self.config.llm_attn_implementation:
+            attn_kwargs['attn_implementation'] = self.config.llm_attn_implementation
+        self.llm = AutoModelForCausalLM.from_config(self.config.llm_config, **attn_kwargs)
+        assert self.config.hidden_size == self.llm.config.hidden_size, "hidden size mismatch"
+        self.text_tokenizer = AutoTokenizer.from_pretrained(self.config.name_or_path)
+        self.visual_tokenizer = AutoModel.from_config(self.config.visual_tokenizer_config,
+                                                      image_processor_name_or_path=self.config.name_or_path)
+        self.vte = VisualEmbedding(
+            self.config.visual_tokenizer_config.vocab_size,
+            self.config.hidden_size,
+            device=self.visual_tokenizer.device,
+            dtype=self.visual_tokenizer.dtype
+        )
+
+        def _merge_modules(modules_list: tuple):
+            merged_modules = []
+            for modules in modules_list:
+                merged_modules.extend(modules if modules else [])
+            return merged_modules
+
+        self._no_split_modules = _merge_modules((self.llm._no_split_modules, self.visual_tokenizer._no_split_modules))
+        self._skip_keys_device_placement = self.llm._skip_keys_device_placement
+        self._keep_in_fp32_modules = _merge_modules(
+            (self.llm._keep_in_fp32_modules, self.visual_tokenizer._keep_in_fp32_modules))
+        self.is_parallelizable = all((self.llm.is_parallelizable, self.visual_tokenizer.is_parallelizable))
+        self.supports_gradient_checkpointing = all(
+            (self.llm.supports_gradient_checkpointing, self.visual_tokenizer.supports_gradient_checkpointing))
+        self._supports_flash_attn_2 = all(
+            (self.llm._supports_flash_attn_2, self.visual_tokenizer._supports_flash_attn_2))
+        self._supports_sdpa = all((self.llm._supports_sdpa, self.visual_tokenizer._supports_sdpa))
+
+    def get_text_tokenizer(self):
+        return self.text_tokenizer
+
+    def get_visual_tokenizer(self):
+        return self.visual_tokenizer
+
+    def tie_weights(self):
+        if not self.config.disable_tie_weight:
+            self.get_llm().tie_weights()
+
+    def get_llm(self):
+        return self.llm
+
+    def get_vte(self):
+        return self.vte
+
+    def get_wte(self):
+        return self.llm.get_input_embeddings()
+
+    def get_conversation_formatter(self) -> ConversationFormatter:
+        if getattr(self, 'conversation_formatter', None) is None:
+            self.conversation_formatter = getattr(import_module(".configuration_ovis", __package__),
+                                                  self.config.conversation_formatter_class)(self.text_tokenizer)
+        return self.conversation_formatter
+
+    def forward(
+        self,
+        input_ids: torch.Tensor,
+        attention_mask: torch.Tensor,
+        labels: Optional[torch.Tensor],
+        pixel_values: List[Optional[torch.Tensor]],
+        **kwargs
+    ):
+        # assert self.training, "`forward` can only be used in training. For inference, use `generate`."
+        _, inputs_embeds, labels, attention_mask = self.merge_multimodal(
+            text_input_ids=input_ids,
+            text_attention_masks=attention_mask,
+            text_labels=labels,
+            pixel_values=pixel_values
+        )
+        return self.llm(inputs_embeds=inputs_embeds, labels=labels, attention_mask=attention_mask, **kwargs)
+
+    def merge_multimodal(
+        self,
+        text_input_ids: torch.Tensor,
+        text_attention_masks: torch.Tensor,
+        text_labels: Optional[torch.Tensor],
+        pixel_values: List[Optional[torch.Tensor]],
+        left_padding: bool = False
+    ):
+        input_device = text_input_ids.device
+        visual_vocab_szie = self.get_visual_tokenizer().config.vocab_size
+        visual_indicator_embeds = self.get_vte()(
+            torch.tensor(
+                list(range(visual_vocab_szie - 5, visual_vocab_szie)),
+                dtype=torch.long,
+                device=self.get_visual_tokenizer().device
+            )
+        ).to(device=input_device)
+
+        if self.training:
+            # When training, to be compatible with deepspeed zero, each sample has to include pixel_value tensor.
+            # For text-only sample, one can simply use a full zero tensor as pixel_value, which will be ignored
+            # (see below in this function); so, the gradient will not be affected.
+            num_images = [x.shape[0] for x in pixel_values]
+            visual_tokens = self.visual_tokenizer(torch.cat([x for x in pixel_values], dim=0))
+            visual_embeds = torch.split(self.get_vte()(visual_tokens).to(dtype=self.dtype, device=input_device),
+                                        split_size_or_sections=num_images, dim=0)
+            visual_input_ids = torch.split(torch.argmax(visual_tokens, dim=-1).to(device=input_device),
+                                           split_size_or_sections=num_images, dim=0)
+            visual_labels = [torch.full(x.shape, IGNORE_ID, dtype=torch.long, device=input_device) for x in
+                             visual_input_ids]
+        else:
+            # When inference, sample can include only text with `None` pixel_value
+            num_images = [x.shape[0] if x is not None else 0 for x in pixel_values]
+            if sum(num_images) > 0:
+                visual_tokens = self.visual_tokenizer(torch.cat([x for x in pixel_values if x is not None], dim=0))
+                visual_embeds = torch.split(self.get_vte()(visual_tokens).to(dtype=self.dtype, device=input_device),
+                                            split_size_or_sections=num_images, dim=0)
+                visual_input_ids = torch.split(torch.argmax(visual_tokens, dim=-1).to(device=input_device),
+                                               split_size_or_sections=num_images, dim=0)
+                visual_labels = [torch.full(x.shape, IGNORE_ID, dtype=torch.long, device=input_device) for x in
+                                 visual_input_ids]
+            else:
+                # just placeholders
+                visual_embeds = [None] * len(num_images)
+                visual_input_ids = [None] * len(num_images)
+                visual_labels = [None] * len(num_images)
+            if text_labels is None:
+                text_labels = torch.full(text_input_ids.shape, IGNORE_ID, dtype=torch.long, device=input_device)
+
+        input_embeds = []
+        attention_masks = []
+        labels = []
+        for text_input_id, text_label, text_attention_mask, visual_embed, visual_input_id, visual_label in zip(
+                text_input_ids, text_labels, text_attention_masks, visual_embeds, visual_input_ids, visual_labels
+        ):
+            placeholder_token_mask = torch.lt(text_input_id, 0)
+            text_embed = self.get_wte()(torch.masked_fill(text_input_id, placeholder_token_mask, 0))
+            for i, indicator_id in enumerate(IMAGE_INDICATOR_IDS):
+                text_embed[text_input_id == indicator_id] = visual_indicator_embeds[i]
+            image_atom_positions = torch.where(torch.eq(text_input_id, IMAGE_ATOM_ID))[0].tolist()
+            if len(image_atom_positions) > 0:
+                input_embed_parts = []
+                attention_mask_parts = []
+                label_parts = []
+                prev_image_atom_position = -1
+                for index, image_atom_position in enumerate(image_atom_positions):
+                    input_embed_parts.append(
+                        text_embed[prev_image_atom_position + 1:image_atom_position, :])
+                    label_parts.append(
+                        text_label[prev_image_atom_position + 1:image_atom_position])
+                    attention_mask_parts.append(
+                        text_attention_mask[prev_image_atom_position + 1:image_atom_position])
+                    input_embed_parts.append(visual_embed[index])
+                    attention_mask_parts.append(
+                        torch.ones_like(visual_label[index], dtype=torch.bool))
+                    label_parts.append(visual_label[index])
+                    prev_image_atom_position = image_atom_position
+                if prev_image_atom_position + 1 < text_input_id.shape[0]:
+                    input_embed_parts.append(
+                        text_embed[prev_image_atom_position + 1:, :])
+                    attention_mask_parts.append(
+                        text_attention_mask[prev_image_atom_position + 1:])
+                    label_parts.append(
+                        text_label[prev_image_atom_position + 1:])
+                input_embed = torch.cat(input_embed_parts, dim=0)
+                attention_mask = torch.cat(attention_mask_parts, dim=0)
+                label = torch.cat(label_parts, dim=0)
+            else:
+                input_embed = text_embed
+                attention_mask = text_attention_mask
+                label = text_label
+                if self.training:
+                    # Make visual_embed & visual_indicator_embeds involved in the backward graph,
+                    # to be compatible with deepspeed zero and ddp.
+                    input_embed += torch.sum(visual_embed * 0.0) + torch.sum(visual_indicator_embeds * 0.0)
+            input_embeds.append(input_embed)
+            attention_masks.append(attention_mask)
+            labels.append(label)
+
+        if self.training:  # padding to self.config.multimodal_max_length for increased training speed
+            padding_size = max(0, self.config.multimodal_max_length - len(input_embeds[0]))
+            input_embeds[0] = torch.nn.ConstantPad2d((0, 0, 0, padding_size), 0.0)(input_embeds[0])
+            attention_masks[0] = torch.nn.ConstantPad1d((0, padding_size), False)(attention_masks[0])
+            labels[0] = torch.nn.ConstantPad1d((0, padding_size), IGNORE_ID)(labels[0])
+        batch_input_embeds = self.pad_truncate_sequence(input_embeds, batch_first=True, padding_value=0.0, left_padding=left_padding)
+        batch_attention_mask = self.pad_truncate_sequence(attention_masks, batch_first=True, padding_value=False, left_padding=left_padding)
+        batch_labels = self.pad_truncate_sequence(labels, batch_first=True, padding_value=IGNORE_ID, left_padding=left_padding)
+
+        return visual_input_ids, batch_input_embeds, batch_labels, batch_attention_mask
+
+    def pad_truncate_sequence(self, sequences: List[torch.Tensor], batch_first: bool = True, padding_value: float = 0.0, left_padding: bool = False) -> torch.Tensor:
+        if left_padding == False:
+            pad_sequence = torch.nn.utils.rnn.pad_sequence(sequences, batch_first=batch_first, padding_value=padding_value)
+            return pad_sequence[:,:self.config.multimodal_max_length]
+        else:
+            pad_sequence = torch.nn.utils.rnn.pad_sequence([i.flip(dims=[0]) for i in sequences],batch_first=True, padding_value=padding_value).flip(dims=[1])
+            return pad_sequence[:,-self.config.multimodal_max_length:]
+
+    def preprocess_inputs(
+        self,
+        text_or_conversations: Union[List[Dict], str],
+        images: Optional[List[PIL.Image.Image]],
+        max_partition=9,
+        generation_preface='',
+        return_labels=False,
+        propagate_exception=True
+    ):
+        # convert text to conversations
+        if isinstance(text_or_conversations, str):
+            conversations = [{
+                "from": "human",
+                "value": text_or_conversations
+            }]
+        elif isinstance(text_or_conversations, list):
+            conversations = text_or_conversations
+        else:
+            raise ValueError(f'Invalid type of `text_or_conversations`, expected `List[Dict]` or `str`,'
+                             f' but got {type(text_or_conversations)}')
+
+        # format conversations
+        prompt, raw_input_ids, raw_labels = self.get_conversation_formatter().format(
+            conversations, generation_preface=generation_preface)
+
+        # place image placeholders
+        input_ids = []
+        labels = []
+        pixel_values = []
+        invalidate_label = False
+        image_token_indices = [i for i, v in enumerate(raw_input_ids) if v == IMAGE_TOKEN_ID]
+        last_image_token_index = -1
+        for i in range(len(image_token_indices)):
+            head = 0 if i == 0 else image_token_indices[i - 1] + 1
+            tail = image_token_indices[i]
+            last_image_token_index = tail
+            input_ids.extend(raw_input_ids[head:tail])
+            labels.extend(raw_labels[head:tail])
+            try:
+                image = images[i]
+                raw_pixel_values, image_placeholders = self.visual_tokenizer.preprocess_image(
+                    image, max_partition=max_partition)
+            except Exception as e:
+                if propagate_exception:
+                    raise e
+                logging.exception(e)
+                invalidate_label = True
+                raw_pixel_values, image_placeholders = self.visual_tokenizer.mock_input()
+            input_ids.extend(image_placeholders)
+            labels.extend([IGNORE_ID] * len(image_placeholders))
+            pixel_values.append(raw_pixel_values)
+        input_ids.extend(raw_input_ids[last_image_token_index + 1:])
+        labels.extend(raw_labels[last_image_token_index + 1:])
+
+        # return tensors
+        input_ids = torch.tensor(input_ids, dtype=torch.long)
+        labels = torch.tensor([IGNORE_ID] * len(labels) if invalidate_label else labels, dtype=torch.long)
+        pixel_values = torch.cat(pixel_values, dim=0) if len(pixel_values) > 0 else None
+
+        if return_labels:
+            return prompt, input_ids, pixel_values, labels
+        else:
+            return prompt, input_ids, pixel_values
+
+    def save_pretrained(
+        self,
+        save_directory: Union[str, os.PathLike],
+        is_main_process: bool = True,
+        state_dict: Optional[dict] = None,
+        save_function: Callable = torch.save,
+        push_to_hub: bool = False,
+        max_shard_size: Union[int, str] = "5GB",
+        safe_serialization: bool = True,
+        variant: Optional[str] = None,
+        token: Optional[Union[str, bool]] = None,
+        save_peft_format: bool = True,
+        **kwargs
+    ):
+        super().save_pretrained(save_directory,
+                                is_main_process=is_main_process,
+                                state_dict=state_dict,
+                                save_function=save_function,
+                                safe_serialization=safe_serialization)
+        self.get_text_tokenizer().save_pretrained(save_directory)
+        self.get_visual_tokenizer().get_image_processor().save_pretrained(save_directory)
+
+    def _get_hybrid_cache_for_llm(self, max_batch_size: int, max_cache_len: int):
+        cache_cls = HybridCache
+        llm = self.get_llm()
+
+        need_new_cache = (
+            not hasattr(llm, "_cache")
+            or (not isinstance(llm._cache, cache_cls))
+            or llm._cache.max_batch_size != max_batch_size
+            or llm._cache.max_cache_len < max_cache_len
+        )
+
+        if need_new_cache:
+            if hasattr(llm.config, "_pre_quantization_dtype"):
+                cache_dtype = llm.config._pre_quantization_dtype
+            else:
+                cache_dtype = llm.dtype
+            llm._cache = cache_cls(
+                config=llm.config,
+                max_batch_size=max_batch_size,
+                max_cache_len=max_cache_len,
+                device=llm.device,
+                dtype=cache_dtype,
+            )
+        else:
+            llm._cache.reset()
+        return llm._cache
+
+    # TODO: support batch generation
+    def generate(
+        self,
+        inputs: Optional[torch.Tensor] = None,
+        **kwargs
+    ) -> Union[GenerateOutput, torch.LongTensor]:
+        _, inputs_embeds, labels, attention_mask = self.merge_multimodal(
+            text_input_ids=inputs,
+            text_attention_masks=kwargs.pop('attention_mask'),
+            text_labels=None,
+            pixel_values=kwargs.pop('pixel_values'),
+            left_padding=True
+        )
+        if getattr(self.generation_config, 'cache_implementation') == 'hybrid':  # mainly for Gemma2
+            kwargs['past_key_values'] = self._get_hybrid_cache_for_llm(
+                getattr(kwargs, "num_beams", inputs_embeds.shape[0]), kwargs['max_new_tokens'] + inputs_embeds.shape[-2])
+            self.get_llm()._supports_cache_class = True
+            kwargs['cache_implementation'] = None
+
+        return self.llm.generate(inputs=None, inputs_embeds=inputs_embeds, attention_mask=attention_mask, **kwargs)

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  }
+}

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.1,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}