Upload folder using huggingface_hub

checkpoint-2000/chat_template.jinja

@@ -0,0 +1,5 @@
+{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}

checkpoint-2000/config.json

@@ -0,0 +1,69 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaLLaDAModelLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_llada.LLaDAConfig",
+    "AutoModel": "modeling_llada.LLaDAModelLM",
+    "AutoModelForCausalLM": "modeling_llada.LLaDAModelLM"
+  },
+  "bos_token_id": 126080,
+  "delay_load": true,
+  "dtype": "bfloat16",
+  "embedding_loss_lambda": 0.5,
+  "embedding_loss_type": "infonce_learnable",
+  "embedding_pool_strategy": "response_tokens",
+  "eos_token_id": 126081,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 16384,
+  "mm_hidden_size": 768,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model,embedding_projection",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "radjepa:AIDElab-IITBombay/RadJEPA",
+  "mm_vision_tower_lr": 1e-06,
+  "model_type": "llada",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 126081,
+  "pos_skipping_range": 4096,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.57.1",
+  "use_auxiliary_embedding_loss": true,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": null,
+  "vocab_size": 126349,
+  "y_encoder_dim": 1024,
+  "y_encoder_name": "abhinand/MedEmbed-large-v0.1"
+}

checkpoint-2000/configuration_llada.py

@@ -0,0 +1,175 @@
+# coding=utf-8
+# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+#
+# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
+# and OPT implementations in this library. It has been modified from its
+# original forms to accommodate minor architectural differences compared
+# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+""" LLaDA model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+LLaDA_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+
+
+class LLaDAConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`LLaDAModel`]. It is used to instantiate an LLaDA
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the LLaDA-8B.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 32000):
+            Vocabulary size of the LLaDA model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`LLaDAModel`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with. 
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/main/perf_train_gpu_many#tensor-parallelism) to understand more about it. This value is
+            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
+            issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum. 
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+    """
+
+    model_type = "llada"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=32000,
+        hidden_size=4096,
+        intermediate_size=11008,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        hidden_act="silu",
+        max_position_embeddings=2048,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=1,
+        eos_token_id=2,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self._rope_scaling_validation()
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+    def _rope_scaling_validation(self):
+        """
+        Validate the `rope_scaling` configuration.
+        """
+        if self.rope_scaling is None:
+            return
+
+        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
+            raise ValueError(
+                "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
+                f"got {self.rope_scaling}"
+            )
+        rope_scaling_type = self.rope_scaling.get("type", None)
+        rope_scaling_factor = self.rope_scaling.get("factor", None)
+        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
+            raise ValueError(
+                f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
+            )
+        if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
+            raise ValueError(f"`rope_scaling`'s factor field must be a float > 1, got {rope_scaling_factor}")

checkpoint-2000/latest

@@ -0,0 +1 @@
+global_step2000

checkpoint-2000/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1426d4f131e32848765a90f9fa8338f4a644ce103c6291b705482638c51220f
+size 4994639360

checkpoint-2000/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4a3a870a4f515f1e895fba8f97fa5f7dfedc3ba36a5e9b8375969b6cc419e6
+size 4999802600

checkpoint-2000/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622f7ca55870a26d128c5091168c64b11e49be9c78bc330468525f160881af0d
+size 4999827272

checkpoint-2000/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4486a62b3444b6671b2061cf92ac1ab7980b20f93d60ee24a580514d5583e900
+size 1937667242

checkpoint-2000/model.safetensors.index.json

@@ -0,0 +1,849 @@
+{
+  "metadata": {
+    "total_parameters": 728321,
+    "total_size": 16931820034
+  },
+  "weight_map": {
+    "embedding_loss_fn.logit_scale": "model-00004-of-00004.safetensors",
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.embedding_projection.proj.0.bias": "model-00004-of-00004.safetensors",
+    "model.embedding_projection.proj.0.weight": "model-00004-of-00004.safetensors",
+    "model.embedding_projection.proj.2.bias": "model-00004-of-00004.safetensors",
+    "model.embedding_projection.proj.2.weight": "model-00004-of-00004.safetensors",
+    "model.image_newline": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.norm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.model.pos_embed": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.embeddings.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.embeddings.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.embeddings.position_embeddings.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.embeddings.token_type_embeddings.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.embeddings.word_embeddings.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.0.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.1.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.10.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.11.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.12.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.13.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.14.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.15.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.16.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.17.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.18.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.19.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.2.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.20.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.21.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.22.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.23.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.3.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.4.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.5.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.6.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.7.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.8.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.attention.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.attention.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.attention.self.key.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.attention.self.key.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.attention.self.query.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.attention.self.query.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.attention.self.value.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.attention.self.value.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.intermediate.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.intermediate.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.output.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.encoder.layer.9.output.dense.weight": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.pooler.dense.bias": "model-00004-of-00004.safetensors",
+    "model.y_encoder.base_model.0.auto_model.pooler.dense.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-2000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb40a4458c9e72a7f1d8c85b3ae935d07fad4e159a23ce47148de5aa7305ac9
+size 16389

checkpoint-2000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a861b5eed890056d53efc68d7d171c187f7fb95c97fba3dd075a0a715d87399
+size 16389

checkpoint-2000/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7268593a09f3f04c55240873078ae152b3f5c892cacab1ba48e57ec65a291281
+size 16404

checkpoint-2000/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29352fe9566b063ec4ebef7fc654e2ded4262d3a4f9db7b0223feee24869096d
+size 16404

checkpoint-2000/rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d09ac763a1adcef2bf4df49f00f7f7871a152f37ee1628b3b0d6307dc155df8
+size 16404

checkpoint-2000/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632f157c6356b0cc0a96d17184cc70bbee6659ec11b5a40aaff4366dae485134
+size 16404

checkpoint-2000/rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ca89da7bffc60ad5da329197beb7a01870d959bdbbc4e60074e0d722140dca
+size 16404

checkpoint-2000/rng_state_15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d598722cdad23db99108b57a480e2cc5a7490492e3d8adc148c1ffb1218107b5
+size 16404

checkpoint-2000/rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0917ef1d32a951ac46f9d7aef4ce8775bc382018bb8c5e141ef696055c0661
+size 16404

checkpoint-2000/rng_state_17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d684ae7b60674391a4725bc249c0b429fce908d09b39b5a304dc1081778831f3
+size 16404

checkpoint-2000/rng_state_18.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ce6c2c3d76c1b842de274d283046b5e55a1c9fac25166137013e62ed16ef7e
+size 16404

checkpoint-2000/rng_state_19.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4ffaed3534aee2a29d3d752d8247290d87b829aa0adf367cb266aff1ae471d
+size 16404

checkpoint-2000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9d0b12d228a0a1524f873c06dba477d4c0ca109104ce01b91b6e13e70bff3c
+size 16389

checkpoint-2000/rng_state_20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd064ef0fabfe96bf7db3aab96c9e6cc05e0a80e2c06deaf7677537dc8ab3b5
+size 16404

checkpoint-2000/rng_state_21.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b41fcfee855dfd7d255da222b343c6b25e3d8440e5ab787860964c390dea9f
+size 16404

checkpoint-2000/rng_state_22.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2493113f0f3bec5ea239e877f553fde077c5710173f1e905ca1f23f7836e531
+size 16404

checkpoint-2000/rng_state_23.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d39456dc7716cc60babbb70a8b7f6605e1f72946c58c2c836481c29417cfb08
+size 16404

checkpoint-2000/rng_state_24.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e2152a2792f48ffbebc9dc15af2ed819dfc56f04f0611e052163100b25ab62
+size 16404

checkpoint-2000/rng_state_25.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:361af5af89e7a00d67fe830cc0d764fe88b002d8f9f3bcf11ff3abbd73eb35e1
+size 16404

checkpoint-2000/rng_state_26.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2896b5f3f08fdcee9cd91ee98455c01d6620e978c83e20a1dcfccbd73e37e2c1
+size 16404

checkpoint-2000/rng_state_27.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1510b51356e22b62a1cfe58911d5de7cfdf8348dfda14be59658f0178290dc
+size 16404

checkpoint-2000/rng_state_28.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d304c97fb350b997a8dbdbb065f0e3e3f7fa6809a02ad7da2808ca98b2c2211
+size 16404

checkpoint-2000/rng_state_29.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be0ac68aaea236f1339f3495a9c29c030ce505fda0e6b5943010cd245d707c3d
+size 16404

checkpoint-2000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17147d81339261eba40ea98a307d42d534c9791e014b827c6916ae73ee0ac517
+size 16389

checkpoint-2000/rng_state_30.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b806e8d04ec3b68848b5ba7b0c284395b073708125df909f35903c9621b70b
+size 16404

checkpoint-2000/rng_state_31.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401ae69e52a854d261a6f4d2bf0770994cd12a3900b20eaceac0b045867866bf
+size 16404

checkpoint-2000/rng_state_32.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a3cf2936b9b1f184e96be398737b2c0cec89ae6159cf5247956369a3a3684f7
+size 16404

checkpoint-2000/rng_state_33.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f6cfeae0e4bc20f7c31c244ea7569748d148e3e8fd39f1b3ae745b8a545500
+size 16404

checkpoint-2000/rng_state_34.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce338f450e8fc88d15b0ad4a5bbbca3f8c9ae8fe50143be9935d118e059b8f22
+size 16404

checkpoint-2000/rng_state_35.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d25041bca3399da01a36a5c8e50a264b5d1320f16b8074f6bd79218ef12cbe
+size 16404

checkpoint-2000/rng_state_36.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:059cf2df08ebaa0d3361da3547027aad2a94d888fadd052931c442ee4dca2d7b
+size 16404

checkpoint-2000/rng_state_37.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a9e0d853aec2f2ecceb9137e6bcf081c6a00b196c36308a318dc42a1cccf68
+size 16404

checkpoint-2000/rng_state_38.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c89dd2cb380a0c3b82fc3a31bb929219a9bec664c209f7d79383a6b09421b1
+size 16404

checkpoint-2000/rng_state_39.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6373564133ed622e08e2e75759a6f3399285d58fc5973f24c0805960115743c9
+size 16404

checkpoint-2000/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a5bf7e122f6b721cb63546e00b49e7650cf627f5723eb606e85ce130785b68
+size 16389

checkpoint-2000/rng_state_40.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3578c3e778a470ceff3cbef51302636b38eb8e15b25405d89d7f5e56f0eaa139
+size 16404

checkpoint-2000/rng_state_41.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3226819809cd8b6286935b961f74e224808d40796d04839233cee1041d22a794
+size 16404

checkpoint-2000/rng_state_42.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03bc4ec6674018d9db1155ef1251d9d8e3b27cb237eaefe3cdd993a85e452d9e
+size 16404

checkpoint-2000/rng_state_43.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f37e3822fda8d78099a34325e419ed7fcb9d40646fce0297a7a20da92250af62
+size 16404

checkpoint-2000/rng_state_44.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59a1f25968c9c532e0fc91fecc681ba83524f69c9d34d3696f3d222909d4b9a
+size 16404

checkpoint-2000/rng_state_45.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f33cead796823f6febe4fee017a5b19819b63c77e17cc711c3268a7fa036f000
+size 16404