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/InternVL3-8B",
+  "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": 3584,
+  "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": 3584,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "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": 28,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "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-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2a1229e924dfbca094559f2338af52970f31b01551ecccb63951aa2c436e55
+size 4991123960

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d5d3ff6e5d365b11a3da99787c23db5aed3219c5638f1283d6b456f17fa45a
+size 4958443072

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e91daca088053fa59a1b70643e1981d8c27280f35b064f4f65677f38ff65a42
+size 4796984024

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee1154ba264d7fa55580e9d273c24f4429ee6e3e8d879351f67daf08ac7ea25
+size 1142280864

model.safetensors.index.json

@@ -0,0 +1,692 @@
+{
+  "metadata": {
+    "total_size": 15888747520
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00003-of-00004.safetensors",
+    "mlp1.0.bias": "model-00004-of-00004.safetensors",
+    "mlp1.0.weight": "model-00004-of-00004.safetensors",
+    "mlp1.1.bias": "model-00004-of-00004.safetensors",
+    "mlp1.1.weight": "model-00004-of-00004.safetensors",
+    "mlp1.3.bias": "model-00004-of-00004.safetensors",
+    "mlp1.3.weight": "model-00004-of-00004.safetensors",
+    "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
+    "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
+    "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.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 +1,1173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.285714285714286,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "advantages_interactive_phase": -7.450580596923828e-09,
+      "clip_ratio": 0.009601324272807688,
+      "clue_civilian_adjusted_reward_mean": 0.04645636805253976,
+      "clue_civilian_advantage_adjustment": -0.0340991875030158,
+      "clue_civilian_baseline": 0.0340991875030158,
+      "clue_civilian_raw_reward_mean": 0.08055555555555557,
+      "clue_civilian_votes_avg": 0.5833333333333333,
+      "clue_invalid_votes": 2.875,
+      "clue_na_votes": 0.375,
+      "clue_spy_adjusted_reward": -0.13936911300005017,
+      "clue_spy_advantage_adjustment": 0.10229755366661651,
+      "clue_spy_baseline": -0.10229755366661651,
+      "clue_spy_raw_reward": -0.24166666666666672,
+      "clue_spy_votes_received": 3.0,
+      "clue_suspicion_potential_psi": 2.4166666666666665,
+      "clue_total_valid_votes": 4.75,
+      "completion_length": 468.671875,
+      "epoch": 0.14285714285714285,
+      "grad_norm": 1.5805621147155762,
+      "kl": 0.0014362335205078125,
+      "learning_rate": 3.5714285714285716e-07,
+      "loss": 0.0009,
+      "loss_interactive_phase": 0.0008710725232958794,
+      "reward": 0.04593749572205778,
+      "reward_original_clue_max": 0.13422530971612442,
+      "reward_original_clue_mean": -2.210607728011897e-09,
+      "reward_original_clue_min": -0.2361905828296588,
+      "reward_original_clue_std": 0.15096539176990595,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 0.18375000000000005,
+      "reward_original_decision_min": -1.5,
+      "reward_original_decision_std": 1.5282191941515817,
+      "reward_original_overall_mean": 0.09187499889469616,
+      "reward_original_overall_std": 1.1872952864471322,
+      "reward_std": 1.1281701095850887,
+      "step": 1
+    },
+    {
+      "advantages_interactive_phase": 1.1699739843606949e-08,
+      "clip_ratio": 0.01009189459728077,
+      "clue_civilian_adjusted_reward_mean": 0.032244541979207814,
+      "clue_civilian_advantage_adjustment": -0.04969990246523662,
+      "clue_civilian_baseline": 0.04969990246523663,
+      "clue_civilian_raw_reward_mean": 0.08194444444444444,
+      "clue_civilian_votes_avg": 0.29166666666666663,
+      "clue_invalid_votes": 3.375,
+      "clue_na_votes": 1.0,
+      "clue_spy_adjusted_reward": -0.09673363023500019,
+      "clue_spy_advantage_adjustment": 0.14909970309833318,
+      "clue_spy_baseline": -0.14909970309833318,
+      "clue_spy_raw_reward": -0.24583333333333335,
+      "clue_spy_votes_received": 2.75,
+      "clue_suspicion_potential_psi": 2.458333333333333,
+      "clue_total_valid_votes": 3.625,
+      "completion_length": 346.546875,
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.9062501192092896,
+      "kl": 0.0015811920166015625,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.0006,
+      "loss_interactive_phase": 0.000601769017521292,
+      "reward": 0.02179688058128391,
+      "reward_original_clue_max": 0.12385744329827358,
+      "reward_original_clue_mean": -1.0743441833859987e-09,
+      "reward_original_clue_min": -0.2033983952724114,
+      "reward_original_clue_std": 0.13295147035012433,
+      "reward_original_decision_max": 1.3687500000000001,
+      "reward_original_decision_mean": 0.08718750000000001,
+      "reward_original_decision_min": -1.5,
+      "reward_original_decision_std": 1.2333472361619537,
+      "reward_original_overall_mean": 0.04359374946282798,
+      "reward_original_overall_std": 1.0888861639122744,
+      "reward_std": 0.9135217889060865,
+      "step": 2
+    },
+    {
+      "advantages_interactive_phase": -3.91155481338501e-08,
+      "clip_ratio": 0.010360982327256352,
+      "clue_civilian_adjusted_reward_mean": -0.012963048645367207,
+      "clue_civilian_advantage_adjustment": -0.06712971531203388,
+      "clue_civilian_baseline": 0.06712971531203388,
+      "clue_civilian_raw_reward_mean": 0.05416666666666666,
+      "clue_civilian_votes_avg": 0.5,
+      "clue_invalid_votes": 4.125,
+      "clue_na_votes": 0.25,
+      "clue_spy_adjusted_reward": 0.03888914454732575,
+      "clue_spy_advantage_adjustment": 0.20138914454732576,
+      "clue_spy_baseline": -0.20138914454732576,
+      "clue_spy_raw_reward": -0.16249999999999998,
+      "clue_spy_votes_received": 2.125,
+      "clue_suspicion_potential_psi": 1.6249999999999998,
+      "clue_total_valid_votes": 3.625,
+      "completion_length": 469.40625,
+      "epoch": 0.42857142857142855,
+      "grad_norm": 1.7866086959838867,
+      "kl": 0.0020046234130859375,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 0.001,
+      "loss_interactive_phase": 0.0009609556873328984,
+      "reward": -0.07253908214457255,
+      "reward_original_clue_max": 0.17909297508117578,
+      "reward_original_clue_mean": -3.4719396715260364e-10,
+      "reward_original_clue_min": -0.1906668791792172,
+      "reward_original_clue_std": 0.148119477615202,
+      "reward_original_decision_max": 0.8700000000000001,
+      "reward_original_decision_mean": -0.29015625,
+      "reward_original_decision_min": -1.5,
+      "reward_original_decision_std": 1.012053904965003,
+      "reward_original_overall_mean": -0.14507812517359697,
+      "reward_original_overall_std": 1.0090200646515894,
+      "reward_std": 1.0390325135884786,
+      "step": 3
+    },
+    {
+      "advantages_interactive_phase": 1.618172973394394e-08,
+      "clip_ratio": 0.011920451768673956,
+      "clue_civilian_adjusted_reward_mean": -0.016897605204000857,
+      "clue_civilian_advantage_adjustment": -0.05578649409288976,
+      "clue_civilian_baseline": 0.05578649409288975,
+      "clue_civilian_raw_reward_mean": 0.038888888888888896,
+      "clue_civilian_votes_avg": 0.5833333333333333,
+      "clue_invalid_votes": 3.75,
+      "clue_na_votes": 0.75,
+      "clue_spy_adjusted_reward": 0.05069280585926233,
+      "clue_spy_advantage_adjustment": 0.16735947252592903,
+      "clue_spy_baseline": -0.16735947252592903,
+      "clue_spy_raw_reward": -0.11666666666666668,
+      "clue_spy_votes_received": 1.75,
+      "clue_suspicion_potential_psi": 1.1666666666666665,
+      "clue_total_valid_votes": 3.5,
+      "completion_length": 349.9765625,
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.8659637570381165,
+      "kl": 0.0020847320556640625,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.0006,
+      "loss_interactive_phase": 0.0005855783383594826,
+      "reward": -0.09585936751868138,
+      "reward_original_clue_max": 0.12609553713896215,
+      "reward_original_clue_mean": -2.438185060966991e-09,
+      "reward_original_clue_min": -0.1539659667175763,
+      "reward_original_clue_std": 0.11102248687112745,
+      "reward_original_decision_max": 1.7175,
+      "reward_original_decision_mean": -0.3834375,
+      "reward_original_decision_min": -1.5,
+      "reward_original_decision_std": 1.318500391473726,
+      "reward_original_overall_mean": -0.1917187512190925,
+      "reward_original_overall_std": 1.0483758882247372,
+      "reward_std": 0.8920968279522142,
+      "step": 4
+    },
+    {
+      "advantages_interactive_phase": -9.313225746154785e-09,
+      "clip_ratio": 0.011668159277178347,
+      "clue_civilian_adjusted_reward_mean": 0.012703904980288123,
+      "clue_civilian_advantage_adjustment": -0.06090720613082299,
+      "clue_civilian_baseline": 0.060907206130823004,
+      "clue_civilian_raw_reward_mean": 0.07361111111111111,
+      "clue_civilian_votes_avg": 0.6666666666666666,
+      "clue_invalid_votes": 3.125,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.038111721525748175,
+      "clue_spy_advantage_adjustment": 0.18272161180758517,
+      "clue_spy_baseline": -0.18272161180758517,
+      "clue_spy_raw_reward": -0.22083333333333333,
+      "clue_spy_votes_received": 2.875,
+      "clue_suspicion_potential_psi": 2.208333333333334,
+      "clue_total_valid_votes": 4.875,
+      "completion_length": 454.71875,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.5932543277740479,
+      "kl": 0.0032215118408203125,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 0.0011,
+      "loss_interactive_phase": 0.0011206967756152153,
+      "reward": 0.020976557431831903,
+      "reward_original_clue_max": 0.14661833481616776,
+      "reward_original_clue_mean": -1.646220952741459e-09,
+      "reward_original_clue_min": -0.24318362303306112,
+      "reward_original_clue_std": 0.15305170150846256,
+      "reward_original_decision_max": 1.6425,
+      "reward_original_decision_mean": 0.08390625000000004,
+      "reward_original_decision_min": -1.5,
+      "reward_original_decision_std": 1.4370029970655516,
+      "reward_original_overall_mean": 0.04195312417688955,
+      "reward_original_overall_std": 1.1718515588438811,
+      "reward_std": 1.1204482532340438,
+      "step": 5
+    },
+    {
+      "advantages_interactive_phase": 1.3998942449688911e-08,
+      "clip_ratio": 0.010447208071127534,
+      "clue_civilian_adjusted_reward_mean": 0.019708324802807216,
+      "clue_civilian_advantage_adjustment": -0.06084723075274834,
+      "clue_civilian_baseline": 0.06084723075274835,
+      "clue_civilian_raw_reward_mean": 0.08055555555555557,
+      "clue_civilian_votes_avg": 0.5833333333333333,
+      "clue_invalid_votes": 1.875,
+      "clue_na_votes": 1.375,
+      "clue_spy_adjusted_reward": -0.05912497942333426,
+      "clue_spy_advantage_adjustment": 0.18254168724333242,
+      "clue_spy_baseline": -0.18254168724333242,
+      "clue_spy_raw_reward": -0.2416666666666667,
+      "clue_spy_votes_received": 3.0,
+      "clue_suspicion_potential_psi": 2.416666666666667,
+      "clue_total_valid_votes": 4.75,
+      "completion_length": 334.2265625,
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.8248350024223328,
+      "kl": 0.0023393630981445312,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.0006,
+      "loss_interactive_phase": 0.0005622203752864152,
+      "reward": 0.0834375066860392,
+      "reward_original_clue_max": 0.1274395314956929,
+      "reward_original_clue_mean": -1.253728150484891e-09,
+      "reward_original_clue_min": -0.188569575974057,
+      "reward_original_clue_std": 0.12904785603086397,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 0.33375000000000005,
+      "reward_original_decision_min": -1.425,
+      "reward_original_decision_std": 1.405177486682367,
+      "reward_original_overall_mean": 0.16687499937313596,
+      "reward_original_overall_std": 1.1144284606169126,
+      "reward_std": 0.9262521229778956,
+      "step": 6
+    },
+    {
+      "advantages_interactive_phase": 2.421438694000244e-08,
+      "clip_ratio": 0.011843746062368155,
+      "clue_civilian_adjusted_reward_mean": 0.06142050400483314,
+      "clue_civilian_advantage_adjustment": -0.09830171821738909,
+      "clue_civilian_baseline": 0.0983017182173891,
+      "clue_civilian_raw_reward_mean": 0.15972222222222224,
+      "clue_civilian_votes_avg": 0.5833333333333333,
+      "clue_invalid_votes": 0.625,
+      "clue_na_votes": 0.25,
+      "clue_spy_adjusted_reward": -0.18426152068943952,
+      "clue_spy_advantage_adjustment": 0.2949051459772272,
+      "clue_spy_baseline": -0.2949051459772272,
+      "clue_spy_raw_reward": -0.47916666666666674,
+      "clue_spy_votes_received": 5.375,
+      "clue_suspicion_potential_psi": 4.791666666666667,
+      "clue_total_valid_votes": 7.125,
+      "completion_length": 403.921875,
+      "epoch": 1.0,
+      "grad_norm": 1.83256995677948,
+      "kl": 0.008373260498046875,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0082,
+      "loss_interactive_phase": 0.008202007971704006,
+      "reward": 0.33738282406500975,
+      "reward_original_clue_max": 0.16317140174540612,
+      "reward_original_clue_mean": -2.1687350280430798e-09,
+      "reward_original_clue_min": -0.2651790850966792,
+      "reward_original_clue_std": 0.1737400336164854,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 1.34953125,
+      "reward_original_decision_min": -1.05,
+      "reward_original_decision_std": 1.2417606105114989,
+      "reward_original_overall_mean": 0.6747656239156326,
+      "reward_original_overall_std": 1.2304992480944565,
+      "reward_std": 1.149772112760493,
+      "step": 7
+    },
+    {
+      "advantages_interactive_phase": 7.101334631443024e-09,
+      "clip_ratio": 0.010323125752620399,
+      "clue_civilian_adjusted_reward_mean": 0.014969077351818358,
+      "clue_civilian_advantage_adjustment": -0.13919758931484832,
+      "clue_civilian_baseline": 0.13919758931484832,
+      "clue_civilian_raw_reward_mean": 0.1541666666666667,
+      "clue_civilian_votes_avg": 0.6249999999999999,
+      "clue_invalid_votes": 0.5,
+      "clue_na_votes": 0.375,
+      "clue_spy_adjusted_reward": -0.0449072601736762,
+      "clue_spy_advantage_adjustment": 0.41759273982632383,
+      "clue_spy_baseline": -0.41759273982632383,
+      "clue_spy_raw_reward": -0.4625,
+      "clue_spy_votes_received": 5.25,
+      "clue_suspicion_potential_psi": 4.625,
+      "clue_total_valid_votes": 7.125,
+      "completion_length": 296.3125,
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.8603692054748535,
+      "kl": 0.00751495361328125,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.0006,
+      "loss_interactive_phase": 0.0005805297987535596,
+      "reward": 0.32882812679327855,
+      "reward_original_clue_max": 0.14714505206208714,
+      "reward_original_clue_mean": -7.029555287255823e-09,
+      "reward_original_clue_min": -0.25208323488394496,
+      "reward_original_clue_std": 0.1584445317000752,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.3153125,
+      "reward_original_decision_min": -1.05,
+      "reward_original_decision_std": 1.3998854722184924,
+      "reward_original_overall_mean": 0.6576562464852225,
+      "reward_original_overall_std": 1.2712911404891047,
+      "reward_std": 1.006177807237865,
+      "step": 8
+    },
+    {
+      "advantages_interactive_phase": 8.754432201385498e-08,
+      "clip_ratio": 0.00764932727906853,
+      "clue_civilian_adjusted_reward_mean": -0.04392835440414705,
+      "clue_civilian_advantage_adjustment": -0.12309502107081373,
+      "clue_civilian_baseline": 0.12309502107081373,
+      "clue_civilian_raw_reward_mean": 0.07916666666666668,
+      "clue_civilian_votes_avg": 1.25,
+      "clue_invalid_votes": 0.375,
+      "clue_na_votes": 0.25,
+      "clue_spy_adjusted_reward": 0.13178503837842287,
+      "clue_spy_advantage_adjustment": 0.36928503837842286,
+      "clue_spy_baseline": -0.36928503837842286,
+      "clue_spy_raw_reward": -0.23750000000000002,
+      "clue_spy_votes_received": 3.625,
+      "clue_suspicion_potential_psi": 2.375,
+      "clue_total_valid_votes": 7.375,
+      "completion_length": 383.28125,
+      "epoch": 1.2857142857142856,
+      "grad_norm": 1.2030161619186401,
+      "kl": 0.021331787109375,
+      "learning_rate": 3.2142857142857147e-06,
+      "loss": 0.0013,
+      "loss_interactive_phase": 0.0013305692409630865,
+      "reward": 0.15667972972003488,
+      "reward_original_clue_max": 0.31233062085321145,
+      "reward_original_clue_mean": -6.208504575678717e-09,
+      "reward_original_clue_min": -0.36730352417905254,
+      "reward_original_clue_std": 0.2591782484917472,
+      "reward_original_decision_max": 1.3687500000000001,
+      "reward_original_decision_mean": 0.6267187500000002,
+      "reward_original_decision_min": -0.7012499999999999,
+      "reward_original_decision_std": 0.7808322541858488,
+      "reward_original_overall_mean": 0.31335937189574775,
+      "reward_original_overall_std": 0.9976451254390301,
+      "reward_std": 0.8997144106280117,
+      "step": 9
+    },
+    {
+      "advantages_interactive_phase": -5.820766091346741e-10,
+      "clip_ratio": 0.009187435440253466,
+      "clue_civilian_adjusted_reward_mean": 0.03822758988085955,
+      "clue_civilian_advantage_adjustment": -0.11732796567469601,
+      "clue_civilian_baseline": 0.11732796567469601,
+      "clue_civilian_raw_reward_mean": 0.15555555555555556,
+      "clue_civilian_votes_avg": 0.7083333333333333,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 0.375,
+      "clue_spy_adjusted_reward": -0.11468278722393674,
+      "clue_spy_advantage_adjustment": 0.35198387944273,
+      "clue_spy_baseline": -0.35198387944273,
+      "clue_spy_raw_reward": -0.4666666666666667,
+      "clue_spy_votes_received": 5.375,
+      "clue_suspicion_potential_psi": 4.666666666666667,
+      "clue_total_valid_votes": 7.5,
+      "completion_length": 267.59375,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.3427386283874512,
+      "kl": 0.0283355712890625,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.002,
+      "loss_interactive_phase": 0.0019903209613403305,
+      "reward": 0.34910156111012686,
+      "reward_original_clue_max": 0.21486971111570505,
+      "reward_original_clue_mean": -4.395339522032804e-09,
+      "reward_original_clue_min": -0.3329915751254489,
+      "reward_original_clue_std": 0.2213489408298035,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 1.39640625,
+      "reward_original_decision_min": -0.052499999999999936,
+      "reward_original_decision_std": 0.777539948847112,
+      "reward_original_overall_mean": 0.6982031228023303,
+      "reward_original_overall_std": 1.1362766329525933,
+      "reward_std": 0.8716088880016916,
+      "step": 10
+    },
+    {
+      "advantages_interactive_phase": 7.450580596923828e-09,
+      "clip_ratio": 0.007512057200074196,
+      "clue_civilian_adjusted_reward_mean": 0.029820853200277782,
+      "clue_civilian_advantage_adjustment": -0.14240136902194445,
+      "clue_civilian_baseline": 0.14240136902194445,
+      "clue_civilian_raw_reward_mean": 0.17222222222222225,
+      "clue_civilian_votes_avg": 0.45833333333333337,
+      "clue_invalid_votes": 0.375,
+      "clue_na_votes": 0.625,
+      "clue_spy_adjusted_reward": -0.08946257515700651,
+      "clue_spy_advantage_adjustment": 0.42720409150966016,
+      "clue_spy_baseline": -0.42720409150966016,
+      "clue_spy_raw_reward": -0.5166666666666667,
+      "clue_spy_votes_received": 5.625,
+      "clue_suspicion_potential_psi": 5.166666666666667,
+      "clue_total_valid_votes": 7.0,
+      "completion_length": 345.90625,
+      "epoch": 1.5714285714285714,
+      "grad_norm": 1.4723293781280518,
+      "kl": 0.03619384765625,
+      "learning_rate": 3.928571428571429e-06,
+      "loss": 0.0017,
+      "loss_interactive_phase": 0.0016628647717880085,
+      "reward": 0.37558594025302955,
+      "reward_original_clue_max": 0.16687582015889904,
+      "reward_original_clue_mean": -3.8890432892298155e-09,
+      "reward_original_clue_min": -0.2556842087822944,
+      "reward_original_clue_std": 0.1723200812438524,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.50234375,
+      "reward_original_decision_min": -0.1274999999999999,
+      "reward_original_decision_std": 0.9362325016572549,
+      "reward_original_overall_mean": 0.7511718730554785,
+      "reward_original_overall_std": 1.2049933860634257,
+      "reward_std": 1.0033885483907903,
+      "step": 11
+    },
+    {
+      "advantages_interactive_phase": 4.249159246683121e-09,
+      "clip_ratio": 0.00809995060262736,
+      "clue_civilian_adjusted_reward_mean": 0.022188266754369242,
+      "clue_civilian_advantage_adjustment": -0.187533955467853,
+      "clue_civilian_baseline": 0.187533955467853,
+      "clue_civilian_raw_reward_mean": 0.20972222222222225,
+      "clue_civilian_votes_avg": 0.33333333333333337,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 0.25,
+      "clue_spy_adjusted_reward": -0.0665648172282207,
+      "clue_spy_advantage_adjustment": 0.5626018494384459,
+      "clue_spy_baseline": -0.5626018494384459,
+      "clue_spy_raw_reward": -0.6291666666666668,
+      "clue_spy_votes_received": 6.625,
+      "clue_suspicion_potential_psi": 6.291666666666667,
+      "clue_total_valid_votes": 7.625,
+      "completion_length": 252.8515625,
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.6337663531303406,
+      "kl": 0.0308074951171875,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.0016,
+      "loss_interactive_phase": 0.0016085498355096206,
+      "reward": 0.4791796885642602,
+      "reward_original_clue_max": 0.13644402464982577,
+      "reward_original_clue_mean": -4.2412782478781774e-09,
+      "reward_original_clue_min": -0.2099872417903439,
+      "reward_original_clue_std": 0.13869593786155765,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.91671875,
+      "reward_original_decision_min": 0.2962500000000001,
+      "reward_original_decision_std": 0.7221503219446256,
+      "reward_original_overall_mean": 0.9583593728793611,
+      "reward_original_overall_std": 1.2329093618898852,
+      "reward_std": 0.8671444384671382,
+      "step": 12
+    },
+    {
+      "advantages_interactive_phase": 1.862645149230957e-08,
+      "clip_ratio": 0.0037154321908019483,
+      "clue_civilian_adjusted_reward_mean": -0.0063334161387741394,
+      "clue_civilian_advantage_adjustment": -0.17300008280544082,
+      "clue_civilian_baseline": 0.1730000828054408,
+      "clue_civilian_raw_reward_mean": 0.16666666666666663,
+      "clue_civilian_votes_avg": 0.75,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": 0.019000245031720445,
+      "clue_spy_advantage_adjustment": 0.5190002450317205,
+      "clue_spy_baseline": -0.5190002450317205,
+      "clue_spy_raw_reward": -0.5,
+      "clue_spy_votes_received": 5.75,
+      "clue_suspicion_potential_psi": 5.000000000000001,
+      "clue_total_valid_votes": 8.0,
+      "completion_length": 337.15625,
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.6522341370582581,
+      "kl": 0.060089111328125,
+      "learning_rate": 4.642857142857144e-06,
+      "loss": 0.0026,
+      "loss_interactive_phase": 0.002614069191622548,
+      "reward": 0.3841406341016882,
+      "reward_original_clue_max": 0.2507983958494952,
+      "reward_original_clue_mean": -8.461504942894327e-10,
+      "reward_original_clue_min": -0.3617781823290228,
+      "reward_original_clue_std": 0.23592987163167928,
+      "reward_original_decision_max": 1.6425,
+      "reward_original_decision_mean": 1.5365625,
+      "reward_original_decision_min": 1.21875,
+      "reward_original_decision_std": 0.183489132426828,
+      "reward_original_overall_mean": 0.7682812495769249,
+      "reward_original_overall_std": 1.0923944210890442,
+      "reward_std": 0.6130125272216156,
+      "step": 13
+    },
+    {
+      "advantages_interactive_phase": 1.6996636986732483e-08,
+      "clip_ratio": 0.00847951346077025,
+      "clue_civilian_adjusted_reward_mean": -0.008037120541629665,
+      "clue_civilian_advantage_adjustment": -0.1774815649860741,
+      "clue_civilian_baseline": 0.1774815649860741,
+      "clue_civilian_raw_reward_mean": 0.16944444444444443,
+      "clue_civilian_votes_avg": 0.6666666666666667,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.25,
+      "clue_spy_adjusted_reward": 0.024111363006878495,
+      "clue_spy_advantage_adjustment": 0.5324446963402119,
+      "clue_spy_baseline": -0.5324446963402119,
+      "clue_spy_raw_reward": -0.5083333333333333,
+      "clue_spy_votes_received": 5.75,
+      "clue_suspicion_potential_psi": 5.083333333333334,
+      "clue_total_valid_votes": 7.75,
+      "completion_length": 263.8359375,
+      "epoch": 2.0,
+      "grad_norm": 0.6224793195724487,
+      "kl": 0.05419921875,
+      "learning_rate": 5e-06,
+      "loss": 0.0029,
+      "loss_interactive_phase": 0.0029011927836108953,
+      "reward": 0.388828133584693,
+      "reward_original_clue_max": 0.2085423028111688,
+      "reward_original_clue_mean": 3.4549737831963967e-10,
+      "reward_original_clue_min": -0.2378369221284988,
+      "reward_original_clue_std": 0.17641129318052418,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 1.5553125000000003,
+      "reward_original_decision_min": 0.3712500000000002,
+      "reward_original_decision_std": 0.668291458945668,
+      "reward_original_overall_mean": 0.777656250172749,
+      "reward_original_overall_std": 1.157252940433482,
+      "reward_std": 0.8331386712800759,
+      "step": 14
+    },
+    {
+      "advantages_interactive_phase": 1.6763806343078613e-08,
+      "clip_ratio": 0.003465894202236086,
+      "clue_civilian_adjusted_reward_mean": 0.023268842590345305,
+      "clue_civilian_advantage_adjustment": -0.18367560185409915,
+      "clue_civilian_baseline": 0.18367560185409915,
+      "clue_civilian_raw_reward_mean": 0.20694444444444446,
+      "clue_civilian_votes_avg": 0.41666666666666663,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.06980651791005336,
+      "clue_spy_advantage_adjustment": 0.55102681542328,
+      "clue_spy_baseline": -0.55102681542328,
+      "clue_spy_raw_reward": -0.6208333333333333,
+      "clue_spy_votes_received": 6.625,
+      "clue_suspicion_potential_psi": 6.208333333333333,
+      "clue_total_valid_votes": 7.875,
+      "completion_length": 355.0625,
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.7302604913711548,
+      "kl": 0.08294677734375,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.0034,
+      "loss_interactive_phase": 0.0033593956904951483,
+      "reward": 0.4744921964982146,
+      "reward_original_clue_max": 0.15940368854312534,
+      "reward_original_clue_mean": 2.465245637836566e-09,
+      "reward_original_clue_min": -0.24915193754399267,
+      "reward_original_clue_std": 0.16536223128526092,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 1.8979687500000002,
+      "reward_original_decision_min": 1.14375,
+      "reward_original_decision_std": 0.34843519072601103,
+      "reward_original_overall_mean": 0.9489843762326229,
+      "reward_original_overall_std": 1.1879908640849528,
+      "reward_std": 0.7276260579460828,
+      "step": 15
+    },
+    {
+      "advantages_interactive_phase": -5.820766091346741e-09,
+      "clip_ratio": 0.006389049158315174,
+      "clue_civilian_adjusted_reward_mean": -0.046890086079656224,
+      "clue_civilian_advantage_adjustment": -0.1635567527463229,
+      "clue_civilian_baseline": 0.1635567527463229,
+      "clue_civilian_raw_reward_mean": 0.11666666666666668,
+      "clue_civilian_votes_avg": 0.625,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 1.875,
+      "clue_spy_adjusted_reward": 0.14067026040217548,
+      "clue_spy_advantage_adjustment": 0.49067026040217543,
+      "clue_spy_baseline": -0.49067026040217543,
+      "clue_spy_raw_reward": -0.35000000000000003,
+      "clue_spy_votes_received": 4.125,
+      "clue_suspicion_potential_psi": 3.5,
+      "clue_total_valid_votes": 6.0,
+      "completion_length": 298.203125,
+      "epoch": 2.2857142857142856,
+      "grad_norm": 18.787372589111328,
+      "kl": 0.0643310546875,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.0227,
+      "loss_interactive_phase": 0.02273198706097901,
+      "reward": 0.2448046847248174,
+      "reward_original_clue_max": 0.31508776732274035,
+      "reward_original_clue_mean": 5.408017063682213e-10,
+      "reward_original_clue_min": -0.296307593000221,
+      "reward_original_clue_std": 0.24153634073282915,
+      "reward_original_decision_max": 1.7925,
+      "reward_original_decision_mean": 0.97921875,
+      "reward_original_decision_min": 0.37125000000000014,
+      "reward_original_decision_std": 0.4794102853203757,
+      "reward_original_overall_mean": 0.4896093752704009,
+      "reward_original_overall_std": 0.942394237518095,
+      "reward_std": 0.732489835712951,
+      "step": 16
+    },
+    {
+      "advantages_interactive_phase": 3.91155481338501e-08,
+      "clip_ratio": 0.003673899220302701,
+      "clue_civilian_adjusted_reward_mean": 0.04772389224517483,
+      "clue_civilian_advantage_adjustment": -0.16199832997704738,
+      "clue_civilian_baseline": 0.16199832997704738,
+      "clue_civilian_raw_reward_mean": 0.2097222222222222,
+      "clue_civilian_votes_avg": 0.20833333333333331,
+      "clue_invalid_votes": 0.375,
+      "clue_na_votes": 0.5,
+      "clue_spy_adjusted_reward": -0.1431716761674981,
+      "clue_spy_advantage_adjustment": 0.4859949904991686,
+      "clue_spy_baseline": -0.4859949904991686,
+      "clue_spy_raw_reward": -0.6291666666666668,
+      "clue_spy_votes_received": 6.5,
+      "clue_suspicion_potential_psi": 6.291666666666667,
+      "clue_total_valid_votes": 7.125,
+      "completion_length": 363.796875,
+      "epoch": 2.4285714285714284,
+      "grad_norm": 1.1137752532958984,
+      "kl": 0.099365234375,
+      "learning_rate": 6.071428571428571e-06,
+      "loss": 0.0042,
+      "loss_interactive_phase": 0.0041947553982026875,
+      "reward": 0.4659375195932758,
+      "reward_original_clue_max": 0.13827404245616234,
+      "reward_original_clue_mean": 1.420066000554221e-10,
+      "reward_original_clue_min": -0.25038849304515226,
+      "reward_original_clue_std": 0.16193395395069143,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 1.86375,
+      "reward_original_decision_min": 0.7200000000000001,
+      "reward_original_decision_std": 0.50161616427093,
+      "reward_original_overall_mean": 0.9318750000710034,
+      "reward_original_overall_std": 1.1870721598954623,
+      "reward_std": 0.8607973168537828,
+      "step": 17
+    },
+    {
+      "advantages_interactive_phase": 2.837623469531536e-09,
+      "clip_ratio": 0.00735139346215874,
+      "clue_civilian_adjusted_reward_mean": -0.0017000992579862158,
+      "clue_civilian_advantage_adjustment": -0.19475565481354176,
+      "clue_civilian_baseline": 0.19475565481354176,
+      "clue_civilian_raw_reward_mean": 0.19305555555555554,
+      "clue_civilian_votes_avg": 0.20833333333333331,
+      "clue_invalid_votes": 0.5,
+      "clue_na_votes": 0.875,
+      "clue_spy_adjusted_reward": 0.0051002900798029355,
+      "clue_spy_advantage_adjustment": 0.5842669567464696,
+      "clue_spy_baseline": -0.5842669567464696,
+      "clue_spy_raw_reward": -0.5791666666666666,
+      "clue_spy_votes_received": 6.0,
+      "clue_suspicion_potential_psi": 5.791666666666667,
+      "clue_total_valid_votes": 6.625,
+      "completion_length": 296.6875,
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.6697026491165161,
+      "kl": 0.083984375,
+      "learning_rate": 6.4285714285714295e-06,
+      "loss": 0.0038,
+      "loss_interactive_phase": 0.003771388641325757,
+      "reward": 0.417656250937927,
+      "reward_original_clue_max": 0.112484931462635,
+      "reward_original_clue_mean": -1.923538928399332e-09,
+      "reward_original_clue_min": -0.12320458815006033,
+      "reward_original_clue_std": 0.09749921717912478,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.6706250000000002,
+      "reward_original_decision_min": -0.27749999999999997,
+      "reward_original_decision_std": 1.025463516531797,
+      "reward_original_overall_mean": 0.8353124990382306,
+      "reward_original_overall_std": 1.2562141688103865,
+      "reward_std": 0.9142232616213656,
+      "step": 18
+    },
+    {
+      "advantages_interactive_phase": 2.421438694000244e-08,
+      "clip_ratio": 0.00690445041982457,
+      "clue_civilian_adjusted_reward_mean": -0.02088481382776897,
+      "clue_civilian_advantage_adjustment": -0.19588481382776896,
+      "clue_civilian_baseline": 0.19588481382776896,
+      "clue_civilian_raw_reward_mean": 0.17500000000000002,
+      "clue_civilian_votes_avg": 0.375,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 1.125,
+      "clue_spy_adjusted_reward": 0.06265442930658618,
+      "clue_spy_advantage_adjustment": 0.5876544293065862,
+      "clue_spy_baseline": -0.5876544293065862,
+      "clue_spy_raw_reward": -0.525,
+      "clue_spy_votes_received": 5.625,
+      "clue_suspicion_potential_psi": 5.249999999999999,
+      "clue_total_valid_votes": 6.75,
+      "completion_length": 345.75,
+      "epoch": 2.7142857142857144,
+      "grad_norm": 1.3586255311965942,
+      "kl": 0.135986328125,
+      "learning_rate": 6.785714285714287e-06,
+      "loss": 0.006,
+      "loss_interactive_phase": 0.00598463078495115,
+      "reward": 0.38964844884614847,
+      "reward_original_clue_max": 0.19217094683455577,
+      "reward_original_clue_mean": -3.044180179635758e-09,
+      "reward_original_clue_min": -0.18790133135573855,
+      "reward_original_clue_std": 0.15165388026680496,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 1.55859375,
+      "reward_original_decision_min": 0.3712500000000002,
+      "reward_original_decision_std": 0.6276860023276215,
+      "reward_original_overall_mean": 0.77929687347791,
+      "reward_original_overall_std": 1.1151671426286367,
+      "reward_std": 0.8916601099963023,
+      "step": 19
+    },
+    {
+      "advantages_interactive_phase": 1.1408701539039612e-08,
+      "clip_ratio": 0.0066332001879345626,
+      "clue_civilian_adjusted_reward_mean": -0.014852289498390544,
+      "clue_civilian_advantage_adjustment": -0.15790784505394606,
+      "clue_civilian_baseline": 0.1579078450539461,
+      "clue_civilian_raw_reward_mean": 0.14305555555555555,
+      "clue_civilian_votes_avg": 0.7083333333333334,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.875,
+      "clue_spy_adjusted_reward": 0.04455685833978199,
+      "clue_spy_advantage_adjustment": 0.4737235250064487,
+      "clue_spy_baseline": -0.47372352500644876,
+      "clue_spy_raw_reward": -0.4291666666666667,
+      "clue_spy_votes_received": 5.0,
+      "clue_suspicion_potential_psi": 4.291666666666667,
+      "clue_total_valid_votes": 7.125,
+      "completion_length": 291.84375,
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.7186980247497559,
+      "kl": 0.120361328125,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.0053,
+      "loss_interactive_phase": 0.005272059410344809,
+      "reward": 0.321093755069639,
+      "reward_original_clue_max": 0.23781143176053088,
+      "reward_original_clue_mean": -2.538847402276667e-09,
+      "reward_original_clue_min": -0.3372735295858061,
+      "reward_original_clue_std": 0.22314844267377926,
+      "reward_original_decision_max": 2.1412500000000003,
+      "reward_original_decision_mean": 1.2843750000000003,
+      "reward_original_decision_min": 0.44625000000000015,
+      "reward_original_decision_std": 0.682584747416193,
+      "reward_original_overall_mean": 0.6421874987305765,
+      "reward_original_overall_std": 1.0984288921667873,
+      "reward_std": 0.8115738822191327,
+      "step": 20
+    },
+    {
+      "advantages_interactive_phase": 1.862645149230957e-09,
+      "clip_ratio": 0.011862117098644376,
+      "clue_civilian_adjusted_reward_mean": -0.011171407247594729,
+      "clue_civilian_advantage_adjustment": -0.1500602961364836,
+      "clue_civilian_baseline": 0.1500602961364836,
+      "clue_civilian_raw_reward_mean": 0.1388888888888889,
+      "clue_civilian_votes_avg": 0.4583333333333333,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 1.875,
+      "clue_spy_adjusted_reward": 0.03351421315180729,
+      "clue_spy_advantage_adjustment": 0.450180879818474,
+      "clue_spy_baseline": -0.450180879818474,
+      "clue_spy_raw_reward": -0.41666666666666674,
+      "clue_spy_votes_received": 4.625,
+      "clue_suspicion_potential_psi": 4.166666666666667,
+      "clue_total_valid_votes": 6.0,
+      "completion_length": 341.484375,
+      "epoch": 3.0,
+      "grad_norm": 2.092695713043213,
+      "kl": 0.1983642578125,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.0115,
+      "loss_interactive_phase": 0.011498338542878628,
+      "reward": 0.29777343789438654,
+      "reward_original_clue_max": 0.180558073555015,
+      "reward_original_clue_mean": -2.147744222486675e-09,
+      "reward_original_clue_min": -0.16238193431746906,
+      "reward_original_clue_std": 0.138092222998997,
+      "reward_original_decision_max": 1.7925,
+      "reward_original_decision_mean": 1.19109375,
+      "reward_original_decision_min": -0.8249999999999998,
+      "reward_original_decision_std": 1.0596252090888885,
+      "reward_original_overall_mean": 0.5955468739261279,
+      "reward_original_overall_std": 1.0734861999424956,
+      "reward_std": 1.0712655663327704,
+      "step": 21
+    },
+    {
+      "advantages_interactive_phase": 2.3166649043560028e-08,
+      "clip_ratio": 0.007374117994913831,
+      "clue_civilian_adjusted_reward_mean": -0.013323967362128385,
+      "clue_civilian_advantage_adjustment": -0.1397128562510173,
+      "clue_civilian_baseline": 0.1397128562510173,
+      "clue_civilian_raw_reward_mean": 0.1263888888888889,
+      "clue_civilian_votes_avg": 0.8333333333333333,
+      "clue_invalid_votes": 0.25,
+      "clue_na_votes": 0.625,
+      "clue_spy_adjusted_reward": 0.03997188807820764,
+      "clue_spy_advantage_adjustment": 0.4191385547448744,
+      "clue_spy_baseline": -0.4191385547448744,
+      "clue_spy_raw_reward": -0.3791666666666667,
+      "clue_spy_votes_received": 4.625,
+      "clue_suspicion_potential_psi": 3.7916666666666665,
+      "clue_total_valid_votes": 7.125,
+      "completion_length": 314.3828125,
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.7247025966644287,
+      "kl": 0.14990234375,
+      "learning_rate": 7.857142857142858e-06,
+      "loss": 0.0065,
+      "loss_interactive_phase": 0.006495335896033794,
+      "reward": 0.27199219820781345,
+      "reward_original_clue_max": 0.20973680630488367,
+      "reward_original_clue_mean": -3.5020443879887897e-09,
+      "reward_original_clue_min": -0.25500620188084894,
+      "reward_original_clue_std": 0.17895936766287218,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 1.0879687500000002,
+      "reward_original_decision_min": -0.55125,
+      "reward_original_decision_std": 1.0594716886601967,
+      "reward_original_overall_mean": 0.5439843732489779,
+      "reward_original_overall_std": 1.143192035744574,
+      "reward_std": 0.8779618775670658,
+      "step": 22
+    },
+    {
+      "advantages_interactive_phase": 1.210719347000122e-08,
+      "clip_ratio": 0.009816105710342526,
+      "clue_civilian_adjusted_reward_mean": 0.012905466579270795,
+      "clue_civilian_advantage_adjustment": -0.13431675564295142,
+      "clue_civilian_baseline": 0.13431675564295142,
+      "clue_civilian_raw_reward_mean": 0.14722222222222223,
+      "clue_civilian_votes_avg": 0.8333333333333334,
+      "clue_invalid_votes": 0.25,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.03871641069401783,
+      "clue_spy_advantage_adjustment": 0.4029502559726489,
+      "clue_spy_baseline": -0.4029502559726489,
+      "clue_spy_raw_reward": -0.44166666666666665,
+      "clue_spy_votes_received": 5.25,
+      "clue_suspicion_potential_psi": 4.416666666666667,
+      "clue_total_valid_votes": 7.75,
+      "completion_length": 349.46875,
+      "epoch": 3.2857142857142856,
+      "grad_norm": 1.495042085647583,
+      "kl": 0.20458984375,
+      "learning_rate": 8.214285714285714e-06,
+      "loss": 0.0098,
+      "loss_interactive_phase": 0.009842151892371476,
+      "reward": 0.3264843803688339,
+      "reward_original_clue_max": 0.18625860761540888,
+      "reward_original_clue_mean": -2.7390513624575563e-09,
+      "reward_original_clue_min": -0.25603524557359103,
+      "reward_original_clue_std": 0.16967942428353516,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.3059375000000002,
+      "reward_original_decision_min": -0.62625,
+      "reward_original_decision_std": 1.2001143050462124,
+      "reward_original_overall_mean": 0.6529687486304744,
+      "reward_original_overall_std": 1.2300136329570874,
+      "reward_std": 1.0827139959652952,
+      "step": 23
+    },
+    {
+      "advantages_interactive_phase": 2.0721927285194397e-08,
+      "clip_ratio": 0.007756809587590396,
+      "clue_civilian_adjusted_reward_mean": -0.04694887868266013,
+      "clue_civilian_advantage_adjustment": -0.11500443423821569,
+      "clue_civilian_baseline": 0.11500443423821569,
+      "clue_civilian_raw_reward_mean": 0.06805555555555555,
+      "clue_civilian_votes_avg": 1.3333333333333333,
+      "clue_invalid_votes": 0.5,
+      "clue_na_votes": 0.125,
+      "clue_spy_adjusted_reward": 0.14084662848473525,
+      "clue_spy_advantage_adjustment": 0.345013295151402,
+      "clue_spy_baseline": -0.345013295151402,
+      "clue_spy_raw_reward": -0.20416666666666672,
+      "clue_spy_votes_received": 3.375,
+      "clue_suspicion_potential_psi": 2.041666666666667,
+      "clue_total_valid_votes": 7.375,
+      "completion_length": 362.4375,
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.721821129322052,
+      "kl": 0.15087890625,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.0064,
+      "loss_interactive_phase": 0.006402550439815968,
+      "reward": 0.12550782238826086,
+      "reward_original_clue_max": 0.2615399846222246,
+      "reward_original_clue_mean": -1.8908112909589436e-09,
+      "reward_original_clue_min": -0.29680578730801793,
+      "reward_original_clue_std": 0.21245343365808805,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 0.50203125,
+      "reward_original_decision_min": -1.125,
+      "reward_original_decision_std": 1.2899370730874167,
+      "reward_original_overall_mean": 0.25101562405459443,
+      "reward_original_overall_std": 1.1078002049178977,
+      "reward_std": 0.8967364060953804,
+      "step": 24
+    },
+    {
+      "advantages_interactive_phase": 1.1175870895385742e-08,
+      "clip_ratio": 0.0030952056986279786,
+      "clue_civilian_adjusted_reward_mean": 0.05641245992546336,
+      "clue_civilian_advantage_adjustment": -0.1352542067412033,
+      "clue_civilian_baseline": 0.1352542067412033,
+      "clue_civilian_raw_reward_mean": 0.19166666666666668,
+      "clue_civilian_votes_avg": 0.5,
+      "clue_invalid_votes": 0.25,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.16923738346885245,
+      "clue_spy_advantage_adjustment": 0.40576261653114754,
+      "clue_spy_baseline": -0.40576261653114754,
+      "clue_spy_raw_reward": -0.575,
+      "clue_spy_votes_received": 6.25,
+      "clue_suspicion_potential_psi": 5.75,
+      "clue_total_valid_votes": 7.75,
+      "completion_length": 378.28125,
+      "epoch": 3.571428571428571,
+      "grad_norm": 1.2147719860076904,
+      "kl": 0.2017822265625,
+      "learning_rate": 8.92857142857143e-06,
+      "loss": 0.0086,
+      "loss_interactive_phase": 0.008552196552045643,
+      "reward": 0.4324218803571566,
+      "reward_original_clue_max": 0.17644798867648273,
+      "reward_original_clue_mean": -9.231155991516748e-10,
+      "reward_original_clue_min": -0.3267729122198718,
+      "reward_original_clue_std": 0.20414503627659822,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.7296875000000003,
+      "reward_original_decision_min": 0.645,
+      "reward_original_decision_std": 0.6397808895425074,
+      "reward_original_overall_mean": 0.8648437495384423,
+      "reward_original_overall_std": 1.219408722443206,
+      "reward_std": 0.876965590677074,
+      "step": 25
+    },
+    {
+      "advantages_interactive_phase": 2.421438694000244e-08,
+      "clip_ratio": 0.005824881722219288,
+      "clue_civilian_adjusted_reward_mean": -0.007093781877094507,
+      "clue_civilian_advantage_adjustment": -0.13209378187709453,
+      "clue_civilian_baseline": 0.13209378187709453,
+      "clue_civilian_raw_reward_mean": 0.125,
+      "clue_civilian_votes_avg": 1.0,
+      "clue_invalid_votes": 0.25,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": 0.021281343083350023,
+      "clue_spy_advantage_adjustment": 0.39628134308335006,
+      "clue_spy_baseline": -0.39628134308335006,
+      "clue_spy_raw_reward": -0.375,
+      "clue_spy_votes_received": 4.75,
+      "clue_suspicion_potential_psi": 3.7499999999999996,
+      "clue_total_valid_votes": 7.75,
+      "completion_length": 333.84375,
+      "epoch": 3.7142857142857144,
+      "grad_norm": 0.8488478660583496,
+      "kl": 0.18359375,
+      "learning_rate": 9.285714285714288e-06,
+      "loss": 0.0078,
+      "loss_interactive_phase": 0.007767571427393705,
+      "reward": 0.27351563694794767,
+      "reward_original_clue_max": 0.25575890463160234,
+      "reward_original_clue_mean": -6.369833735996033e-10,
+      "reward_original_clue_min": -0.3290713434253468,
+      "reward_original_clue_std": 0.22778135711245912,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 1.0940625000000002,
+      "reward_original_decision_min": -0.1274999999999999,
+      "reward_original_decision_std": 0.8632276294383053,
+      "reward_original_overall_mean": 0.5470312496815084,
+      "reward_original_overall_std": 1.1264277840598063,
+      "reward_std": 0.8660217167160729,
+      "step": 26
+    },
+    {
+      "advantages_interactive_phase": -7.450580596923828e-09,
+      "clip_ratio": 0.0031035091960802674,
+      "clue_civilian_adjusted_reward_mean": 0.03245208673288981,
+      "clue_civilian_advantage_adjustment": -0.1689368021559991,
+      "clue_civilian_baseline": 0.1689368021559991,
+      "clue_civilian_raw_reward_mean": 0.2013888888888889,
+      "clue_civilian_votes_avg": 0.4583333333333333,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": -0.09735625958223877,
+      "clue_spy_advantage_adjustment": 0.5068104070844279,
+      "clue_spy_baseline": -0.5068104070844279,
+      "clue_spy_raw_reward": -0.6041666666666666,
+      "clue_spy_votes_received": 6.5,
+      "clue_suspicion_potential_psi": 6.041666666666667,
+      "clue_total_valid_votes": 7.875,
+      "completion_length": 306.40625,
+      "epoch": 3.857142857142857,
+      "grad_norm": 1.9208674430847168,
+      "kl": 0.3026123046875,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 0.0125,
+      "loss_interactive_phase": 0.01246593298856169,
+      "reward": 0.46124999631323677,
+      "reward_original_clue_max": 0.1545202636139022,
+      "reward_original_clue_mean": 1.5410765849196983e-10,
+      "reward_original_clue_min": -0.24859110312991783,
+      "reward_original_clue_std": 0.16558966332718913,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.845,
+      "reward_original_decision_min": 0.7200000000000002,
+      "reward_original_decision_std": 0.7004523304839636,
+      "reward_original_overall_mean": 0.9225000000770541,
+      "reward_original_overall_std": 1.2500439582236307,
+      "reward_std": 0.8922832234684476,
+      "step": 27
+    },
+    {
+      "advantages_interactive_phase": 9.66247171163559e-09,
+      "clip_ratio": 0.004918134000035934,
+      "clue_civilian_adjusted_reward_mean": -0.03922444833702034,
+      "clue_civilian_advantage_adjustment": -0.168391115003687,
+      "clue_civilian_baseline": 0.168391115003687,
+      "clue_civilian_raw_reward_mean": 0.12916666666666665,
+      "clue_civilian_votes_avg": 1.0,
+      "clue_invalid_votes": 0.125,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": 0.11767334568750121,
+      "clue_spy_advantage_adjustment": 0.5051733456875013,
+      "clue_spy_baseline": -0.5051733456875013,
+      "clue_spy_raw_reward": -0.3875000000000001,
+      "clue_spy_votes_received": 4.875,
+      "clue_suspicion_potential_psi": 3.8750000000000004,
+      "clue_total_valid_votes": 7.875,
+      "completion_length": 290.8359375,
+      "epoch": 4.0,
+      "grad_norm": 0.778830885887146,
+      "kl": 0.2080078125,
+      "learning_rate": 1e-05,
+      "loss": 0.0085,
+      "loss_interactive_phase": 0.008535244385711849,
+      "reward": 0.29144531737351337,
+      "reward_original_clue_max": 0.2624036269472061,
+      "reward_original_clue_mean": 1.691100571209192e-10,
+      "reward_original_clue_min": -0.2589547295967252,
+      "reward_original_clue_std": 0.20231139453953567,
+      "reward_original_decision_max": 2.49,
+      "reward_original_decision_mean": 1.16578125,
+      "reward_original_decision_min": -0.05249999999999988,
+      "reward_original_decision_std": 0.9492047780780623,
+      "reward_original_overall_mean": 0.582890625084555,
+      "reward_original_overall_std": 1.1522968480359421,
+      "reward_std": 0.8734021281821482,
+      "step": 28
+    },
+    {
+      "advantages_interactive_phase": 2.60770320892334e-08,
+      "clip_ratio": 0.004597238206770271,
+      "clue_civilian_adjusted_reward_mean": -0.017886474267241367,
+      "clue_civilian_advantage_adjustment": -0.13455314093390802,
+      "clue_civilian_baseline": 0.13455314093390805,
+      "clue_civilian_raw_reward_mean": 0.11666666666666667,
+      "clue_civilian_votes_avg": 1.125,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": 0.05365942077661086,
+      "clue_spy_advantage_adjustment": 0.4036594207766109,
+      "clue_spy_baseline": -0.4036594207766109,
+      "clue_spy_raw_reward": -0.35,
+      "clue_spy_votes_received": 4.625,
+      "clue_suspicion_potential_psi": 3.5,
+      "clue_total_valid_votes": 8.0,
+      "completion_length": 304.515625,
+      "epoch": 4.142857142857143,
+      "grad_norm": 1.3750234842300415,
+      "kl": 0.3173828125,
+      "learning_rate": 9.999611462404874e-06,
+      "loss": 0.0125,
+      "loss_interactive_phase": 0.012478827498853207,
+      "reward": 0.26496095041194656,
+      "reward_original_clue_max": 0.26774659185022603,
+      "reward_original_clue_mean": -5.062783100737156e-10,
+      "reward_original_clue_min": -0.31947364534085654,
+      "reward_original_clue_std": 0.23106213560541738,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 1.05984375,
+      "reward_original_decision_min": -0.05249999999999988,
+      "reward_original_decision_std": 0.8307205925127058,
+      "reward_original_overall_mean": 0.529921874746861,
+      "reward_original_overall_std": 1.1095292288061827,
+      "reward_std": 0.8888411754368172,
+      "step": 29
+    },
+    {
+      "advantages_interactive_phase": 3.259629011154175e-09,
+      "clip_ratio": 0.004411640649777837,
+      "clue_civilian_adjusted_reward_mean": -0.019376439787606455,
+      "clue_civilian_advantage_adjustment": -0.10826532867649533,
+      "clue_civilian_baseline": 0.10826532867649533,
+      "clue_civilian_raw_reward_mean": 0.08888888888888888,
+      "clue_civilian_votes_avg": 1.3333333333333333,
+      "clue_invalid_votes": 0.0,
+      "clue_na_votes": 0.0,
+      "clue_spy_adjusted_reward": 0.058129320628341516,
+      "clue_spy_advantage_adjustment": 0.3247959872950082,
+      "clue_spy_baseline": -0.3247959872950082,
+      "clue_spy_raw_reward": -0.2666666666666667,
+      "clue_spy_votes_received": 4.0,
+      "clue_suspicion_potential_psi": 2.6666666666666665,
+      "clue_total_valid_votes": 8.0,
+      "completion_length": 261.4453125,
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.8253775238990784,
+      "kl": 0.2550048828125,
+      "learning_rate": 9.998445910004082e-06,
+      "loss": 0.0103,
+      "loss_interactive_phase": 0.010343844187445939,
+      "reward": 0.19875000170890966,
+      "reward_original_clue_max": 0.2470865782057527,
+      "reward_original_clue_mean": 3.1638053678631484e-10,
+      "reward_original_clue_min": -0.258379067343329,
+      "reward_original_clue_std": 0.19545089761013185,
+      "reward_original_decision_max": 2.06625,
+      "reward_original_decision_mean": 0.7949999999999999,
+      "reward_original_decision_min": -0.47625000000000006,
+      "reward_original_decision_std": 1.1225616644698808,
+      "reward_original_overall_mean": 0.3975000001581903,
+      "reward_original_overall_std": 1.1179099397348429,
+      "reward_std": 0.8648673956089749,
+      "step": 30
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 5,
+  "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 sha256:288760a4083a1d67c4b30eb2ff32cb35216c1d0721ef56ee3ff7b95c4b257b91
+size 8977