Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,33 @@
+{
+  "</box>": 151673,
+  "</img>": 151666,
+  "</quad>": 151669,
+  "</ref>": 151671,
+  "</tool_call>": 151658,
+  "<IMG_CONTEXT>": 151667,
+  "<box>": 151672,
+  "<img>": 151665,
+  "<quad>": 151668,
+  "<ref>": 151670,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,225 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "/mnt/localssd/models/InternVL3-14B",
+  "architectures": [
+    "InternVLChatModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
+    "AutoModel": "modeling_internvl_chat.InternVLChatModel",
+    "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
+  },
+  "downsample_ratio": 0.5,
+  "dynamic_image_size": true,
+  "force_image_size": 448,
+  "hidden_size": 5120,
+  "image_fold": null,
+  "llm_config": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
+    "add_cross_attention": false,
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "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": 151643,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "min_length": 0,
+    "model_type": "qwen2",
+    "moe_config": null,
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 40,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 48,
+    "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,
+    "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-06,
+    "rope_scaling": {
+      "factor": 2.0,
+      "rope_type": "dynamic",
+      "type": "dynamic"
+    },
+    "rope_theta": 1000000.0,
+    "sep_token_id": null,
+    "sliding_window": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.49.0",
+    "typical_p": 1.0,
+    "use_bfloat16": true,
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151674
+  },
+  "max_dynamic_patch": 12,
+  "min_dynamic_patch": 1,
+  "model_type": "internvl_chat",
+  "pad2square": false,
+  "ps_version": "v2",
+  "select_layer": -1,
+  "system_message": null,
+  "template": "internvl2_5",
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "use_backbone_lora": 0,
+  "use_cache": false,
+  "use_llm_lora": 0,
+  "use_thumbnail": true,
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
+    "add_cross_attention": false,
+    "architectures": [
+      "InternVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+      "AutoConfig": "configuration_intern_vit.InternVisionConfig",
+      "AutoModel": "modeling_intern_vit.InternVisionModel"
+    },
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "capacity_factor": 1.2,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "eval_capacity_factor": 1.4,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 448,
+    "initializer_factor": 0.1,
+    "initializer_range": 1e-10,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "laux_allreduce": "all_nodes",
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "intern_vit_6b",
+    "moe_coeff_ratio": 0.5,
+    "moe_intermediate_size": 768,
+    "moe_output_scale": 4.0,
+    "no_repeat_ngram_size": 0,
+    "noisy_gate_policy": "RSample_before",
+    "norm_type": "layer_norm",
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_experts": 8,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "num_routed_experts": 4,
+    "num_shared_experts": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qk_normalization": false,
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "shared_expert_intermediate_size": 3072,
+    "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,
+    "transformers_version": "4.49.0",
+    "typical_p": 1.0,
+    "use_bfloat16": true,
+    "use_flash_attn": true,
+    "use_moe": false,
+    "use_residual": true,
+    "use_rts": false,
+    "use_weighted_residual": false
+  }
+}

configuration_intern_vit.py

@@ -0,0 +1,120 @@
+# --------------------------------------------------------
+# InternVL
+# Copyright (c) 2024 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+
+import os
+from typing import Union
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+
+class InternVisionConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to
+    instantiate a vision encoder according to the specified arguments, defining the model architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        num_channels (`int`, *optional*, defaults to 3):
+            Number of color channels in the input images (e.g., 3 for RGB).
+        patch_size (`int`, *optional*, defaults to 14):
+            The size (resolution) of each patch.
+        image_size (`int`, *optional*, defaults to 224):
+            The size (resolution) of each image.
+        qkv_bias (`bool`, *optional*, defaults to `False`):
+            Whether to add a bias to the queries and values in the self-attention layers.
+        hidden_size (`int`, *optional*, defaults to 3200):
+            Dimensionality of the encoder layers and the pooler layer.
+        num_attention_heads (`int`, *optional*, defaults to 25):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        intermediate_size (`int`, *optional*, defaults to 12800):
+            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
+        qk_normalization (`bool`, *optional*, defaults to `True`):
+            Whether to normalize the queries and keys in the self-attention layers.
+        num_hidden_layers (`int`, *optional*, defaults to 48):
+            Number of hidden layers in the Transformer encoder.
+        use_flash_attn (`bool`, *optional*, defaults to `True`):
+            Whether to use flash attention mechanism.
+        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
+            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
+            `"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported.
+        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
+            The epsilon used by the layer normalization layers.
+        dropout (`float`, *optional*, defaults to 0.0):
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
+        drop_path_rate (`float`, *optional*, defaults to 0.0):
+            Dropout rate for stochastic depth.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        initializer_factor (`float`, *optional*, defaults to 0.1):
+            A factor for layer scale.
+    """
+
+    model_type = 'intern_vit_6b'
+
+    def __init__(
+            self,
+            num_channels=3,
+            patch_size=14,
+            image_size=224,
+            qkv_bias=False,
+            hidden_size=3200,
+            num_attention_heads=25,
+            intermediate_size=12800,
+            qk_normalization=True,
+            num_hidden_layers=48,
+            use_flash_attn=True,
+            hidden_act='gelu',
+            norm_type='rms_norm',
+            layer_norm_eps=1e-6,
+            dropout=0.0,
+            drop_path_rate=0.0,
+            attention_dropout=0.0,
+            initializer_range=0.02,
+            initializer_factor=0.1,
+            **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.dropout = dropout
+        self.drop_path_rate = drop_path_rate
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_channels = num_channels
+        self.patch_size = patch_size
+        self.image_size = image_size
+        self.initializer_range = initializer_range
+        self.initializer_factor = initializer_factor
+        self.attention_dropout = attention_dropout
+        self.layer_norm_eps = layer_norm_eps
+        self.hidden_act = hidden_act
+        self.norm_type = norm_type
+        self.qkv_bias = qkv_bias
+        self.qk_normalization = qk_normalization
+        self.use_flash_attn = use_flash_attn
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> 'PretrainedConfig':
+        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
+
+        if 'vision_config' in config_dict:
+            config_dict = config_dict['vision_config']
+
+        if 'model_type' in config_dict and hasattr(cls, 'model_type') and config_dict['model_type'] != cls.model_type:
+            logger.warning(
+                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
+                f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
+            )
+
+        return cls.from_dict(config_dict, **kwargs)

configuration_internvl_chat.py

@@ -0,0 +1,97 @@
+# --------------------------------------------------------
+# InternVL
+# Copyright (c) 2024 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+
+import copy
+
+from transformers import AutoConfig, LlamaConfig, Qwen2Config
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+from .configuration_intern_vit import InternVisionConfig
+
+logger = logging.get_logger(__name__)
+
+
+class InternVLChatConfig(PretrainedConfig):
+    model_type = 'internvl_chat'
+    is_composition = True
+
+    def __init__(
+            self,
+            vision_config=None,
+            llm_config=None,
+            use_backbone_lora=0,
+            use_llm_lora=0,
+            select_layer=-1,
+            force_image_size=None,
+            downsample_ratio=0.5,
+            template=None,
+            dynamic_image_size=False,
+            use_thumbnail=False,
+            ps_version='v1',
+            min_dynamic_patch=1,
+            max_dynamic_patch=6,
+            **kwargs):
+        super().__init__(**kwargs)
+
+        if vision_config is None:
+            vision_config = {'architectures': ['InternVisionModel']}
+            logger.info('vision_config is None. Initializing the InternVisionConfig with default values.')
+
+        if llm_config is None:
+            llm_config = {'architectures': ['Qwen2ForCausalLM']}
+            logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
+
+        self.vision_config = InternVisionConfig(**vision_config)
+        if llm_config.get('architectures')[0] == 'LlamaForCausalLM':
+            self.llm_config = LlamaConfig(**llm_config)
+        elif llm_config.get('architectures')[0] == 'Qwen2ForCausalLM':
+            self.llm_config = Qwen2Config(**llm_config)
+        else:
+            raise ValueError('Unsupported architecture: {}'.format(llm_config.get('architectures')[0]))
+        self.use_backbone_lora = use_backbone_lora
+        self.use_llm_lora = use_llm_lora
+        self.select_layer = select_layer
+        self.force_image_size = force_image_size
+        self.downsample_ratio = downsample_ratio
+        self.template = template
+        self.dynamic_image_size = dynamic_image_size
+        self.use_thumbnail = use_thumbnail
+        self.ps_version = ps_version  # pixel shuffle version
+        self.min_dynamic_patch = min_dynamic_patch
+        self.max_dynamic_patch = max_dynamic_patch
+        # By default, we use tie_word_embeddings=False for models of all sizes.
+        self.tie_word_embeddings = self.llm_config.tie_word_embeddings
+
+        logger.info(f'vision_select_layer: {self.select_layer}')
+        logger.info(f'ps_version: {self.ps_version}')
+        logger.info(f'min_dynamic_patch: {self.min_dynamic_patch}')
+        logger.info(f'max_dynamic_patch: {self.max_dynamic_patch}')
+
+    def to_dict(self):
+        """
+        Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`].
+
+        Returns:
+            `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,
+        """
+        output = copy.deepcopy(self.__dict__)
+        output['vision_config'] = self.vision_config.to_dict()
+        output['llm_config'] = self.llm_config.to_dict()
+        output['model_type'] = self.__class__.model_type
+        output['use_backbone_lora'] = self.use_backbone_lora
+        output['use_llm_lora'] = self.use_llm_lora
+        output['select_layer'] = self.select_layer
+        output['force_image_size'] = self.force_image_size
+        output['downsample_ratio'] = self.downsample_ratio
+        output['template'] = self.template
+        output['dynamic_image_size'] = self.dynamic_image_size
+        output['use_thumbnail'] = self.use_thumbnail
+        output['ps_version'] = self.ps_version
+        output['min_dynamic_patch'] = self.min_dynamic_patch
+        output['max_dynamic_patch'] = self.max_dynamic_patch
+
+        return output

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5523007b852d041ceb2170c1bd1a1f5b959d1eb8ebd26f95f97d9da606a8383
+size 4987315704

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be27aa837e137ed02ac0da814da7462383c958d3555f016dba9fb9b78b3497b
+size 4954848952

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026caebde881ea648f4f41439ada753eed5dedae2e9f802189cd6718269eea82
+size 4954849016

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:038878d8e60f73ef490947b4620e0aad13929d7a049a5b15cc988de900fc4eab
+size 4954849016

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8eb7bf29858be83089bb5a3d6ae854bd0b29b231e48023eaeae2e5e98fc51ba
+size 4954849016

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf25d9545303b1d6ea8cfe3141aa7da0509dee589a203c4994df8db3ceed6c00
+size 3780366368

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5866bde0cb394b1280c45ba2e0f83515f9b570b3adb1deb325f17f9584ba71ce
+size 1647551136

model.safetensors.index.json

@@ -0,0 +1,932 @@
+{
+  "metadata": {
+    "total_size": 30234513408
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00007-of-00007.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.41.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.norm.weight": "model-00006-of-00007.safetensors",
+    "mlp1.0.bias": "model-00007-of-00007.safetensors",
+    "mlp1.0.weight": "model-00007-of-00007.safetensors",
+    "mlp1.1.bias": "model-00007-of-00007.safetensors",
+    "mlp1.1.weight": "model-00007-of-00007.safetensors",
+    "mlp1.3.bias": "model-00007-of-00007.safetensors",
+    "mlp1.3.weight": "model-00007-of-00007.safetensors",
+    "vision_model.embeddings.class_embedding": "model-00001-of-00007.safetensors",
+    "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00007.safetensors",
+    "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00007.safetensors",
+    "vision_model.embeddings.position_embedding": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.ls1": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.ls2": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00007.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fd9ff0fc12bf369c22e095353fd3ad2ea4417ecbcac16d15a1ba2a9080331f
+size 11423715

tokenizer_config.json

@@ -0,0 +1,281 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "</img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<IMG_CONTEXT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "</quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "</ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "</box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 12288,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,793 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4285714285714286,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "advantages_interactive_phase": 5.21540641784668e-08,
+      "clip_ratio": 0.002584722707979381,
+      "clue_civilian_adjusted_reward_mean": 0.08771249903044148,
+      "clue_civilian_advantage_adjustment": -0.031731945414002975,
+      "clue_civilian_baseline": 0.031731945414002975,
+      "clue_civilian_raw_reward_mean": 0.11944444444444444,
+      "clue_civilian_votes_avg": 0.9166666666666666,
+      "clue_invalid_votes": 0.25,
+      "clue_na_votes": 0.5,
+      "clue_spy_adjusted_reward": -0.2631374983427426,
+      "clue_spy_advantage_adjustment": 0.0951958349905908,
+      "clue_spy_baseline": -0.09519583499059077,
+      "clue_spy_raw_reward": -0.3583333333333334,
+      "clue_spy_votes_received": 4.5,
+      "clue_suspicion_potential_psi": 3.583333333333333,
+      "clue_total_valid_votes": 7.25,
+      "completion_length": 407.25,
+      "epoch": 0.07142857142857142,
+      "grad_norm": 1.2433040142059326,
+      "kl": 0.0005679130554199219,
+      "learning_rate": 1.7857142857142858e-07,
+      "loss": -0.0,
+      "loss_interactive_phase": -3.3905053896887694e-05,
+      "reward": 0.2564062759988185,
+      "reward_original_clue_max": 0.2350291658628525,
+      "reward_original_clue_mean": -3.1285454088481046e-10,
+      "reward_original_clue_min": -0.46045416493714897,
+      "reward_original_clue_std": 0.28835276263619397,
+      "reward_original_decision_max": 1.7925000000000002,
+      "reward_original_decision_mean": 1.0256250000000002,
+      "reward_original_decision_min": -0.2024999999999999,
+      "reward_original_decision_std": 0.7726940363403899,
+      "reward_original_overall_mean": 0.5128124998435728,
+      "reward_original_overall_std": 1.0697578828306928,
+      "reward_std": 0.9357707818732628,
+      "step": 1
+    },
+    {
+      "advantages_interactive_phase": 0.0,
+      "clip_ratio": 0.0051095280214212835,
+      "clue_civilian_adjusted_reward_mean": 0.10492066951681192,
+      "clue_civilian_advantage_adjustment": -0.07007933048318807,
+      "clue_civilian_baseline": 0.07007933048318808,
+      "clue_civilian_raw_reward_mean": 0.17500000000000002,
+      "clue_civilian_votes_avg": 0.5,
+      "clue_invalid_votes": 0.75,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.3147620110663121,
+      "clue_spy_advantage_adjustment": 0.21023798893368797,
+      "clue_spy_baseline": -0.210237988933688,
+      "clue_spy_raw_reward": -0.525,
+      "clue_spy_votes_received": 5.75,
+      "clue_suspicion_potential_psi": 5.25,
+      "clue_total_valid_votes": 7.25,
+      "completion_length": 397.46875,
+      "epoch": 0.14285714285714285,
+      "grad_norm": 1.371312141418457,
+      "kl": 0.0006885528564453125,
+      "learning_rate": 3.5714285714285716e-07,
+      "loss": 0.0007,
+      "loss_interactive_phase": 0.0007444359362125397,
+      "reward": 0.3700781248427577,
+      "reward_original_clue_max": 0.15492066951681194,
+      "reward_original_clue_mean": -6.289690699691486e-10,
+      "reward_original_clue_min": -0.3147620110663121,
+      "reward_original_clue_std": 0.19281140686888587,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.4803125000000001,
+      "reward_original_decision_min": -1.2,
+      "reward_original_decision_std": 1.59591282301647,
+      "reward_original_overall_mean": 0.7401562496855154,
+      "reward_original_overall_std": 1.3657579641721083,
+      "reward_std": 1.2174014707993186,
+      "step": 2
+    },
+    {
+      "advantages_interactive_phase": 4.842877388000488e-08,
+      "clip_ratio": 0.0007538875506725162,
+      "clue_civilian_adjusted_reward_mean": 0.12562594927052595,
+      "clue_civilian_advantage_adjustment": -0.12159627295169628,
+      "clue_civilian_baseline": 0.12159627295169628,
+      "clue_civilian_raw_reward_mean": 0.24722222222222223,
+      "clue_civilian_votes_avg": 0.08333333333333333,
+      "clue_invalid_votes": 0.25,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.37687785516342853,
+      "clue_spy_advantage_adjustment": 0.36478881150323816,
+      "clue_spy_baseline": -0.36478881150323816,
+      "clue_spy_raw_reward": -0.7416666666666667,
+      "clue_spy_votes_received": 7.5,
+      "clue_suspicion_potential_psi": 7.416666666666667,
+      "clue_total_valid_votes": 7.75,
+      "completion_length": 393.53125,
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.8251210451126099,
+      "kl": 0.0004444122314453125,
+      "learning_rate": 5.357142857142857e-07,
+      "loss": 0.0002,
+      "loss_interactive_phase": 0.00019339301616128068,
+      "reward": 0.5648437737548964,
+      "reward_original_clue_max": 0.13395928260385928,
+      "reward_original_clue_mean": -1.8379626744169375e-09,
+      "reward_original_clue_min": -0.37687785516342853,
+      "reward_original_clue_std": 0.21884174474271245,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 2.2593750000000004,
+      "reward_original_decision_min": 0.6450000000000001,
+      "reward_original_decision_std": 0.6101763961142712,
+      "reward_original_overall_mean": 1.1296874990810188,
+      "reward_original_overall_std": 1.2986833005622422,
+      "reward_std": 0.9166028871871728,
+      "step": 3
+    },
+    {
+      "advantages_interactive_phase": 2.2351741790771484e-08,
+      "clip_ratio": 0.0032811127603054047,
+      "clue_civilian_adjusted_reward_mean": 0.0853481829901718,
+      "clue_civilian_advantage_adjustment": -0.16465181700982823,
+      "clue_civilian_baseline": 0.1646518170098282,
+      "clue_civilian_raw_reward_mean": 0.25,
+      "clue_civilian_votes_avg": 0.0,
+      "clue_invalid_votes": 0.5,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.25604456244642393,
+      "clue_spy_advantage_adjustment": 0.4939554375535762,
+      "clue_spy_baseline": -0.4939554375535762,
+      "clue_spy_raw_reward": -0.75,
+      "clue_spy_votes_received": 7.5,
+      "clue_suspicion_potential_psi": 7.5,
+      "clue_total_valid_votes": 7.5,
+      "completion_length": 344.3125,
+      "epoch": 0.2857142857142857,
+      "grad_norm": 1.0190212726593018,
+      "kl": 0.0007681846618652344,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.0007,
+      "loss_interactive_phase": 0.0007185182575994986,
+      "reward": 0.5601562603336266,
+      "reward_original_clue_max": 0.0853481829901718,
+      "reward_original_clue_mean": -3.368977119846961e-09,
+      "reward_original_clue_min": -0.25604456244642393,
+      "reward_original_clue_std": 0.14782739510790294,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 2.240625,
+      "reward_original_decision_min": 0.4950000000000001,
+      "reward_original_decision_std": 0.6597842331967323,
+      "reward_original_overall_mean": 1.1203124983155115,
+      "reward_original_overall_std": 1.3090146002752656,
+      "reward_std": 0.9217685370436844,
+      "step": 4
+    },
+    {
+      "advantages_interactive_phase": 1.4901161193847656e-08,
+      "clip_ratio": 0.0019974790047854185,
+      "clue_civilian_adjusted_reward_mean": -0.01773556045992832,
+      "clue_civilian_advantage_adjustment": -0.17606889379326165,
+      "clue_civilian_baseline": 0.17606889379326168,
+      "clue_civilian_raw_reward_mean": 0.15833333333333333,
+      "clue_civilian_votes_avg": 0.75,
+      "clue_invalid_votes": 0.25,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": 0.05320667828412917,
+      "clue_spy_advantage_adjustment": 0.5282066782841293,
+      "clue_spy_baseline": -0.5282066782841293,
+      "clue_spy_raw_reward": -0.47500000000000003,
+      "clue_spy_votes_received": 5.5,
+      "clue_suspicion_potential_psi": 4.75,
+      "clue_total_valid_votes": 7.75,
+      "completion_length": 370.09375,
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.8577920794487,
+      "kl": 0.0006928443908691406,
+      "learning_rate": 8.928571428571429e-07,
+      "loss": 0.0005,
+      "loss_interactive_phase": 0.0005262520039650553,
+      "reward": 0.35296875725710214,
+      "reward_original_clue_max": 0.22693185055057774,
+      "reward_original_clue_mean": -7.73913948551308e-10,
+      "reward_original_clue_min": -0.2914607327263769,
+      "reward_original_clue_std": 0.20123490064546354,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.4118750000000002,
+      "reward_original_decision_min": 0.6450000000000001,
+      "reward_original_decision_std": 0.7169369187427281,
+      "reward_original_overall_mean": 0.7059374996130431,
+      "reward_original_overall_std": 1.1841187534341855,
+      "reward_std": 0.8593206136231444,
+      "step": 5
+    },
+    {
+      "advantages_interactive_phase": -3.725290298461914e-09,
+      "clip_ratio": 0.00132036826107651,
+      "clue_civilian_adjusted_reward_mean": 0.03812369614552404,
+      "clue_civilian_advantage_adjustment": -0.17854297052114265,
+      "clue_civilian_baseline": 0.17854297052114262,
+      "clue_civilian_raw_reward_mean": 0.21666666666666665,
+      "clue_civilian_votes_avg": 0.25,
+      "clue_invalid_votes": 0.5,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.11437108812675251,
+      "clue_spy_advantage_adjustment": 0.5356289118732476,
+      "clue_spy_baseline": -0.5356289118732476,
+      "clue_spy_raw_reward": -0.65,
+      "clue_spy_votes_received": 6.75,
+      "clue_suspicion_potential_psi": 6.500000000000001,
+      "clue_total_valid_votes": 7.5,
+      "completion_length": 354.96875,
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.9956780672073364,
+      "kl": 0.0007185935974121094,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": -0.0001,
+      "loss_interactive_phase": -0.00014633889668402844,
+      "reward": 0.48070312315671865,
+      "reward_original_clue_max": 0.10080573748512417,
+      "reward_original_clue_mean": 7.745490707145031e-11,
+      "reward_original_clue_min": -0.17705312946635263,
+      "reward_original_clue_std": 0.11842617275634101,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.9228125,
+      "reward_original_decision_min": 0.6450000000000001,
+      "reward_original_decision_std": 0.7445730501102412,
+      "reward_original_overall_mean": 0.9614062500387276,
+      "reward_original_overall_std": 1.2891040179069748,
+      "reward_std": 0.911813245859539,
+      "step": 6
+    },
+    {
+      "advantages_interactive_phase": -3.725290298461914e-09,
+      "clip_ratio": 0.0015976644353941083,
+      "clue_civilian_adjusted_reward_mean": 0.039737953869895995,
+      "clue_civilian_advantage_adjustment": -0.19915093501899292,
+      "clue_civilian_baseline": 0.19915093501899292,
+      "clue_civilian_raw_reward_mean": 0.23888888888888893,
+      "clue_civilian_votes_avg": 0.08333333333333333,
+      "clue_invalid_votes": 0.5,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.11921386776846599,
+      "clue_spy_advantage_adjustment": 0.5974527988982007,
+      "clue_spy_baseline": -0.5974527988982007,
+      "clue_spy_raw_reward": -0.7166666666666668,
+      "clue_spy_votes_received": 7.25,
+      "clue_suspicion_potential_psi": 7.166666666666667,
+      "clue_total_valid_votes": 7.5,
+      "completion_length": 358.5625,
+      "epoch": 0.5,
+      "grad_norm": 0.9679809808731079,
+      "kl": 0.00067901611328125,
+      "learning_rate": 1.25e-06,
+      "loss": 0.0004,
+      "loss_interactive_phase": 0.00040471651209372794,
+      "reward": 0.5336718727524312,
+      "reward_original_clue_max": 0.04807128720322933,
+      "reward_original_clue_mean": -1.5396944986340033e-09,
+      "reward_original_clue_min": -0.11921386776846599,
+      "reward_original_clue_std": 0.07232113752656728,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 2.1346875,
+      "reward_original_decision_min": 0.6450000000000001,
+      "reward_original_decision_std": 0.7122144496533938,
+      "reward_original_overall_mean": 1.0673437492301527,
+      "reward_original_overall_std": 1.3073998563678253,
+      "reward_std": 0.9209611501888031,
+      "step": 7
+    },
+    {
+      "advantages_interactive_phase": 0.0,
+      "clip_ratio": 0.0,
+      "clue_civilian_adjusted_reward_mean": 0.04686206659827747,
+      "clue_civilian_advantage_adjustment": -0.2198046000683892,
+      "clue_civilian_baseline": 0.2198046000683892,
+      "clue_civilian_raw_reward_mean": 0.26666666666666666,
+      "clue_civilian_votes_avg": 0.0,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.14058619817316526,
+      "clue_spy_advantage_adjustment": 0.6594138018268348,
+      "clue_spy_baseline": -0.6594138018268348,
+      "clue_spy_raw_reward": -0.8,
+      "clue_spy_votes_received": 8.0,
+      "clue_suspicion_potential_psi": 8.0,
+      "clue_total_valid_votes": 8.0,
+      "completion_length": 354.46875,
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.018345005810260773,
+      "kl": 0.0010480880737304688,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.0,
+      "loss_interactive_phase": 4.1909603169187903e-05,
+      "reward": 0.6225000001013543,
+      "reward_original_clue_max": 0.04686206659827747,
+      "reward_original_clue_mean": 4.0541678868188935e-10,
+      "reward_original_clue_min": -0.14058619817316526,
+      "reward_original_clue_std": 0.08116747959369053,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 2.49,
+      "reward_original_decision_min": 2.49,
+      "reward_original_decision_std": 0.0,
+      "reward_original_overall_mean": 1.2450000002027086,
+      "reward_original_overall_std": 1.2463404450342257,
+      "reward_std": 0.6231702225171128,
+      "step": 8
+    },
+    {
+      "advantages_interactive_phase": 1.4901161193847656e-08,
+      "clip_ratio": 0.0013714100932702422,
+      "clue_civilian_adjusted_reward_mean": 0.013246197368885609,
+      "clue_civilian_advantage_adjustment": -0.23397602485333663,
+      "clue_civilian_baseline": 0.23397602485333663,
+      "clue_civilian_raw_reward_mean": 0.24722222222222223,
+      "clue_civilian_votes_avg": 0.08333333333333333,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.25,
+      "clue_spy_adjusted_reward": -0.03973858191124918,
+      "clue_spy_advantage_adjustment": 0.7019280847554175,
+      "clue_spy_baseline": -0.7019280847554175,
+      "clue_spy_raw_reward": -0.7416666666666668,
+      "clue_spy_votes_received": 7.5,
+      "clue_suspicion_potential_psi": 7.416666666666667,
+      "clue_total_valid_votes": 7.75,
+      "completion_length": 356.40625,
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.699692964553833,
+      "kl": 0.0015583038330078125,
+      "learning_rate": 1.6071428571428574e-06,
+      "loss": 0.0004,
+      "loss_interactive_phase": 0.00038320242219924694,
+      "reward": 0.5742187580877937,
+      "reward_original_clue_max": 0.05717585752144352,
+      "reward_original_clue_mean": 2.548851910783023e-09,
+      "reward_original_clue_min": -0.10033490873047377,
+      "reward_original_clue_std": 0.06355237824583888,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 2.296875,
+      "reward_original_decision_min": 1.6425,
+      "reward_original_decision_std": 0.3365977523320678,
+      "reward_original_overall_mean": 1.1484375012744261,
+      "reward_original_overall_std": 1.2551185340937816,
+      "reward_std": 0.7611898854999166,
+      "step": 9
+    },
+    {
+      "advantages_interactive_phase": 3.725290298461914e-09,
+      "clip_ratio": 0.001366270735161379,
+      "clue_civilian_adjusted_reward_mean": -0.059309172584389475,
+      "clue_civilian_advantage_adjustment": -0.21486472813994506,
+      "clue_civilian_baseline": 0.21486472813994506,
+      "clue_civilian_raw_reward_mean": 0.15555555555555556,
+      "clue_civilian_votes_avg": 0.8333333333333334,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": 0.1779275289602213,
+      "clue_spy_advantage_adjustment": 0.6445941956268879,
+      "clue_spy_baseline": -0.6445941956268879,
+      "clue_spy_raw_reward": -0.4666666666666667,
+      "clue_spy_votes_received": 5.5,
+      "clue_suspicion_potential_psi": 4.666666666666667,
+      "clue_total_valid_votes": 8.0,
+      "completion_length": 343.15625,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.2527297735214233,
+      "kl": 0.0028228759765625,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 0.0001,
+      "loss_interactive_phase": 7.36040783522185e-05,
+      "reward": 0.35765625256308603,
+      "reward_original_clue_max": 0.2685985786248518,
+      "reward_original_clue_mean": 2.8017632224680566e-09,
+      "reward_original_clue_min": -0.2666468889156867,
+      "reward_original_clue_std": 0.1992278658615879,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.430625,
+      "reward_original_decision_min": 0.7950000000000002,
+      "reward_original_decision_std": 0.8205883464776965,
+      "reward_original_overall_mean": 0.7153125014008818,
+      "reward_original_overall_std": 1.2216102597312402,
+      "reward_std": 0.8780663816728329,
+      "step": 10
+    },
+    {
+      "advantages_interactive_phase": 6.693881005048752e-10,
+      "clip_ratio": 0.004991011635866016,
+      "clue_civilian_adjusted_reward_mean": -0.04567275066805051,
+      "clue_civilian_advantage_adjustment": -0.19567275066805054,
+      "clue_civilian_baseline": 0.1956727506680505,
+      "clue_civilian_raw_reward_mean": 0.15000000000000002,
+      "clue_civilian_votes_avg": 0.5,
+      "clue_invalid_votes": 1.0,
+      "clue_na_votes": 0.5,
+      "clue_spy_adjusted_reward": 0.13701824806425392,
+      "clue_spy_advantage_adjustment": 0.587018248064254,
+      "clue_spy_baseline": -0.5870182480642541,
+      "clue_spy_raw_reward": -0.45000000000000007,
+      "clue_spy_votes_received": 5.0,
+      "clue_suspicion_potential_psi": 4.5,
+      "clue_total_valid_votes": 6.5,
+      "completion_length": 235.921875,
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.8721132874488831,
+      "kl": 0.002773284912109375,
+      "learning_rate": 1.9642857142857144e-06,
+      "loss": 0.0005,
+      "loss_interactive_phase": 0.0004736769915325567,
+      "reward": 0.29531250008845045,
+      "reward_original_clue_max": 0.20618216237456027,
+      "reward_original_clue_mean": -9.849743937140332e-10,
+      "reward_original_clue_min": -0.13983666497835684,
+      "reward_original_clue_std": 0.1368323967219738,
+      "reward_original_decision_max": 1.7925000000000002,
+      "reward_original_decision_mean": 1.1812500000000001,
+      "reward_original_decision_min": -1.35,
+      "reward_original_decision_std": 1.1320284073138736,
+      "reward_original_overall_mean": 0.5906249995075128,
+      "reward_original_overall_std": 1.1670051800865369,
+      "reward_std": 0.9567088851163008,
+      "step": 11
+    },
+    {
+      "advantages_interactive_phase": -3.14321368932724e-09,
+      "clip_ratio": 0.0038724591431673616,
+      "clue_civilian_adjusted_reward_mean": -0.008785893217789213,
+      "clue_civilian_advantage_adjustment": -0.18934144877334477,
+      "clue_civilian_baseline": 0.18934144877334477,
+      "clue_civilian_raw_reward_mean": 0.18055555555555555,
+      "clue_civilian_votes_avg": 0.5833333333333333,
+      "clue_invalid_votes": 0.25,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": 0.02635767431215162,
+      "clue_spy_advantage_adjustment": 0.5680243409788184,
+      "clue_spy_baseline": -0.5680243409788184,
+      "clue_spy_raw_reward": -0.5416666666666666,
+      "clue_spy_votes_received": 6.0,
+      "clue_suspicion_potential_psi": 5.416666666666667,
+      "clue_total_valid_votes": 7.75,
+      "completion_length": 246.625,
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.7324309945106506,
+      "kl": 0.00567626953125,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.0001,
+      "loss_interactive_phase": 0.00011773800360970199,
+      "reward": 0.4059374980945672,
+      "reward_original_clue_max": 0.14291362995359996,
+      "reward_original_clue_mean": -1.3353040019190021e-09,
+      "reward_original_clue_min": -0.18288577552067203,
+      "reward_original_clue_std": 0.12596317030740456,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.6237500000000002,
+      "reward_original_decision_min": -0.2024999999999999,
+      "reward_original_decision_std": 1.074720395910213,
+      "reward_original_overall_mean": 0.8118749993323481,
+      "reward_original_overall_std": 1.2771047271239024,
+      "reward_std": 0.9275944294133416,
+      "step": 12
+    },
+    {
+      "advantages_interactive_phase": -1.3969838619232178e-09,
+      "clip_ratio": 0.0023974677897058427,
+      "clue_civilian_adjusted_reward_mean": 0.04101557244224265,
+      "clue_civilian_advantage_adjustment": -0.19231776089109068,
+      "clue_civilian_baseline": 0.19231776089109068,
+      "clue_civilian_raw_reward_mean": 0.23333333333333334,
+      "clue_civilian_votes_avg": 0.25,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.12304671695689096,
+      "clue_spy_advantage_adjustment": 0.5769532830431091,
+      "clue_spy_baseline": -0.5769532830431091,
+      "clue_spy_raw_reward": -0.7,
+      "clue_spy_votes_received": 7.25,
+      "clue_suspicion_potential_psi": 7.0,
+      "clue_total_valid_votes": 8.0,
+      "completion_length": 210.28125,
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.5045397281646729,
+      "kl": 0.00478363037109375,
+      "learning_rate": 2.321428571428572e-06,
+      "loss": 0.0005,
+      "loss_interactive_phase": 0.00048686014633858576,
+      "reward": 0.543046874324623,
+      "reward_original_clue_max": 0.0926421892012342,
+      "reward_original_clue_mean": 9.245925032541624e-11,
+      "reward_original_clue_min": -0.1996733337158825,
+      "reward_original_clue_std": 0.12189595123623381,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 2.1721875,
+      "reward_original_decision_min": 1.6425,
+      "reward_original_decision_std": 0.41029417323884826,
+      "reward_original_overall_mean": 1.0860937500462298,
+      "reward_original_overall_std": 1.2643971390572388,
+      "reward_std": 0.7581803483663598,
+      "step": 13
+    },
+    {
+      "advantages_interactive_phase": 2.0954757928848267e-09,
+      "clip_ratio": 0.0020283911435399204,
+      "clue_civilian_adjusted_reward_mean": 0.05121031242321445,
+      "clue_civilian_advantage_adjustment": -0.21545635424345222,
+      "clue_civilian_baseline": 0.21545635424345222,
+      "clue_civilian_raw_reward_mean": 0.26666666666666666,
+      "clue_civilian_votes_avg": 0.0,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.15363092704954806,
+      "clue_spy_advantage_adjustment": 0.6463690729504521,
+      "clue_spy_baseline": -0.6463690729504521,
+      "clue_spy_raw_reward": -0.8,
+      "clue_spy_votes_received": 8.0,
+      "clue_suspicion_potential_psi": 8.0,
+      "clue_total_valid_votes": 8.0,
+      "completion_length": 183.859375,
+      "epoch": 1.0,
+      "grad_norm": 0.18229803442955017,
+      "kl": 0.0092926025390625,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0004,
+      "loss_interactive_phase": 0.000439425501099322,
+      "reward": 0.6225000016864939,
+      "reward_original_clue_max": 0.05121031242321445,
+      "reward_original_clue_mean": 2.5550238227228794e-09,
+      "reward_original_clue_min": -0.15363092704954806,
+      "reward_original_clue_std": 0.08869885856305201,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 2.49,
+      "reward_original_decision_min": 2.49,
+      "reward_original_decision_std": 0.0,
+      "reward_original_overall_mean": 1.245000001277512,
+      "reward_original_overall_std": 1.246600563317156,
+      "reward_std": 0.6556885250171602,
+      "step": 14
+    },
+    {
+      "advantages_interactive_phase": 5.681067705154419e-08,
+      "clip_ratio": 0.0055811598431319,
+      "clue_civilian_adjusted_reward_mean": -0.10015091660615269,
+      "clue_civilian_advantage_adjustment": -0.19459536105059716,
+      "clue_civilian_baseline": 0.19459536105059716,
+      "clue_civilian_raw_reward_mean": 0.09444444444444446,
+      "clue_civilian_votes_avg": 1.1666666666666667,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.5,
+      "clue_spy_adjusted_reward": 0.3004527607937906,
+      "clue_spy_advantage_adjustment": 0.5837860941271239,
+      "clue_spy_baseline": -0.5837860941271239,
+      "clue_spy_raw_reward": -0.2833333333333334,
+      "clue_spy_votes_received": 4.0,
+      "clue_suspicion_potential_psi": 2.833333333333333,
+      "clue_total_valid_votes": 7.5,
+      "completion_length": 184.53125,
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.9797484874725342,
+      "kl": 0.01348876953125,
+      "learning_rate": 2.6785714285714285e-06,
+      "loss": 0.0008,
+      "loss_interactive_phase": 0.0008396641351282597,
+      "reward": 0.20812502909129682,
+      "reward_original_clue_max": 0.3913555161541046,
+      "reward_original_clue_mean": 2.743833119045469e-09,
+      "reward_original_clue_min": -0.37438700529980007,
+      "reward_original_clue_std": 0.2806904116111977,
+      "reward_original_decision_max": 1.7925000000000002,
+      "reward_original_decision_mean": 0.8325000000000001,
+      "reward_original_decision_min": -0.05249999999999988,
+      "reward_original_decision_std": 0.6255204643156431,
+      "reward_original_overall_mean": 0.4162500013719166,
+      "reward_original_overall_std": 0.9969133151443759,
+      "reward_std": 0.7991549877324183,
+      "step": 15
+    },
+    {
+      "advantages_interactive_phase": 1.4901161193847656e-08,
+      "clip_ratio": 0.002903845568653196,
+      "clue_civilian_adjusted_reward_mean": 0.005040981183978218,
+      "clue_civilian_advantage_adjustment": -0.18384790770491066,
+      "clue_civilian_baseline": 0.18384790770491066,
+      "clue_civilian_raw_reward_mean": 0.18888888888888888,
+      "clue_civilian_votes_avg": 0.3333333333333333,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 1.0,
+      "clue_spy_adjusted_reward": -0.015122934206462435,
+      "clue_spy_advantage_adjustment": 0.5515437324602043,
+      "clue_spy_baseline": -0.5515437324602043,
+      "clue_spy_raw_reward": -0.5666666666666667,
+      "clue_spy_votes_received": 6.0,
+      "clue_suspicion_potential_psi": 5.666666666666666,
+      "clue_total_valid_votes": 7.0,
+      "completion_length": 159.234375,
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.6889950037002563,
+      "kl": 0.0163726806640625,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.0007,
+      "loss_interactive_phase": 0.0006972870178287849,
+      "reward": 0.4293750080346727,
+      "reward_original_clue_max": 0.2209372383356327,
+      "reward_original_clue_mean": 2.3363680504151496e-09,
+      "reward_original_clue_min": -0.24768585802478357,
+      "reward_original_clue_std": 0.1979054302315365,
+      "reward_original_decision_max": 1.7925000000000002,
+      "reward_original_decision_mean": 1.7175000000000002,
+      "reward_original_decision_min": 1.6425,
+      "reward_original_decision_std": 0.07499999999999998,
+      "reward_original_overall_mean": 0.8587500011681842,
+      "reward_original_overall_std": 1.0506449735796681,
+      "reward_std": 0.6603923040944453,
+      "step": 16
+    },
+    {
+      "advantages_interactive_phase": 1.9907020032405853e-08,
+      "clip_ratio": 0.002717321884119883,
+      "clue_civilian_adjusted_reward_mean": 0.05820738437851754,
+      "clue_civilian_advantage_adjustment": -0.197348171177038,
+      "clue_civilian_baseline": 0.197348171177038,
+      "clue_civilian_raw_reward_mean": 0.25555555555555554,
+      "clue_civilian_votes_avg": 0.08333333333333333,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.17462214309271265,
+      "clue_spy_advantage_adjustment": 0.5920445235739541,
+      "clue_spy_baseline": -0.5920445235739541,
+      "clue_spy_raw_reward": -0.7666666666666666,
+      "clue_spy_votes_received": 7.75,
+      "clue_suspicion_potential_psi": 7.666666666666667,
+      "clue_total_valid_votes": 8.0,
+      "completion_length": 157.890625,
+      "epoch": 1.2142857142857142,
+      "grad_norm": 0.7511361837387085,
+      "kl": 0.0189208984375,
+      "learning_rate": 3.0357142857142856e-06,
+      "loss": 0.0007,
+      "loss_interactive_phase": 0.0007001502526691183,
+      "reward": 0.5960156355811876,
+      "reward_original_clue_max": 0.06654071771185087,
+      "reward_original_clue_mean": 2.510709987135762e-09,
+      "reward_original_clue_min": -0.17462214309271265,
+      "reward_original_clue_std": 0.10440314691834049,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 2.3840625,
+      "reward_original_decision_min": 1.6425,
+      "reward_original_decision_std": 0.2802842795159051,
+      "reward_original_overall_mean": 1.1920312512553553,
+      "reward_original_overall_std": 1.2616114851538425,
+      "reward_std": 0.7544503553064706,
+      "step": 17
+    },
+    {
+      "advantages_interactive_phase": -7.683411240577698e-09,
+      "clip_ratio": 0.0030201186309568584,
+      "clue_civilian_adjusted_reward_mean": 0.020999861840676374,
+      "clue_civilian_advantage_adjustment": -0.21233347149265697,
+      "clue_civilian_baseline": 0.21233347149265697,
+      "clue_civilian_raw_reward_mean": 0.23333333333333334,
+      "clue_civilian_votes_avg": 0.25,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.06299957715521307,
+      "clue_spy_advantage_adjustment": 0.637000422844787,
+      "clue_spy_baseline": -0.637000422844787,
+      "clue_spy_raw_reward": -0.7,
+      "clue_spy_votes_received": 7.25,
+      "clue_suspicion_potential_psi": 7.0,
+      "clue_total_valid_votes": 8.0,
+      "completion_length": 151.125,
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.9981189370155334,
+      "kl": 0.01995849609375,
+      "learning_rate": 3.2142857142857147e-06,
+      "loss": 0.0009,
+      "loss_interactive_phase": 0.0008631020464235917,
+      "reward": 0.5430468716812205,
+      "reward_original_clue_max": 0.06212192914646331,
+      "reward_original_clue_mean": 2.0917040131213094e-09,
+      "reward_original_clue_min": -0.13194723859334168,
+      "reward_original_clue_std": 0.08127783461529633,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 2.1721875,
+      "reward_original_decision_min": 0.7950000000000002,
+      "reward_original_decision_std": 0.647262544369561,
+      "reward_original_overall_mean": 1.0860937510458522,
+      "reward_original_overall_std": 1.2803237874072,
+      "reward_std": 0.8395660886546574,
+      "step": 18
+    },
+    {
+      "advantages_interactive_phase": 1.501757651567459e-08,
+      "clip_ratio": 0.0030361030949279666,
+      "clue_civilian_adjusted_reward_mean": -0.011421993250583344,
+      "clue_civilian_advantage_adjustment": -0.20308865991725003,
+      "clue_civilian_baseline": 0.20308865991725003,
+      "clue_civilian_raw_reward_mean": 0.19166666666666665,
+      "clue_civilian_votes_avg": 0.25,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 1.25,
+      "clue_spy_adjusted_reward": 0.034265987400023845,
+      "clue_spy_advantage_adjustment": 0.6092659874000239,
+      "clue_spy_baseline": -0.6092659874000239,
+      "clue_spy_raw_reward": -0.575,
+      "clue_spy_votes_received": 6.0,
+      "clue_suspicion_potential_psi": 5.75,
+      "clue_total_valid_votes": 6.75,
+      "completion_length": 171.984375,
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.9874958992004395,
+      "kl": 0.0203857421875,
+      "learning_rate": 3.3928571428571435e-06,
+      "loss": 0.0009,
+      "loss_interactive_phase": 0.0008809004793874919,
+      "reward": 0.43406250798680535,
+      "reward_original_clue_max": 0.1831368831893539,
+      "reward_original_clue_mean": 1.912068458426175e-09,
+      "reward_original_clue_min": -0.2102928890399134,
+      "reward_original_clue_std": 0.15410096528694653,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.73625,
+      "reward_original_decision_min": 0.9450000000000001,
+      "reward_original_decision_std": 0.4920069847428916,
+      "reward_original_overall_mean": 0.8681250009560342,
+      "reward_original_overall_std": 1.1337558540425332,
+      "reward_std": 0.7743000447239295,
+      "step": 19
+    },
+    {
+      "advantages_interactive_phase": 1.932494342327118e-08,
+      "clip_ratio": 0.005017287214286625,
+      "clue_civilian_adjusted_reward_mean": -0.07107897274252634,
+      "clue_civilian_advantage_adjustment": -0.19885675052030413,
+      "clue_civilian_baseline": 0.19885675052030413,
+      "clue_civilian_raw_reward_mean": 0.1277777777777778,
+      "clue_civilian_votes_avg": 0.41666666666666663,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 2.5,
+      "clue_spy_adjusted_reward": 0.21323692668717445,
+      "clue_spy_advantage_adjustment": 0.5965702600205078,
+      "clue_spy_baseline": -0.5965702600205078,
+      "clue_spy_raw_reward": -0.3833333333333333,
+      "clue_spy_votes_received": 4.25,
+      "clue_suspicion_potential_psi": 3.833333333333334,
+      "clue_total_valid_votes": 5.5,
+      "completion_length": 180.1875,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.7904020547866821,
+      "kl": 0.0189208984375,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.0013,
+      "loss_interactive_phase": 0.00130526622524485,
+      "reward": 0.2721093851911965,
+      "reward_original_clue_max": 0.32675487424165234,
+      "reward_original_clue_mean": 2.1148988550018233e-09,
+      "reward_original_clue_min": -0.19293025363033758,
+      "reward_original_clue_std": 0.2220694051243503,
+      "reward_original_decision_max": 1.7925000000000002,
+      "reward_original_decision_mean": 1.0884375,
+      "reward_original_decision_min": 0.795,
+      "reward_original_decision_std": 0.3255402311751499,
+      "reward_original_overall_mean": 0.5442187510574495,
+      "reward_original_overall_std": 0.9174309347926513,
+      "reward_std": 0.6698880425273843,
+      "step": 20
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7fe05f1463e0c7cf59fcb0b709a9a8b713dfba3059311b58f9e1d91c62de32
+size 8913