Model save

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+base_model: HuggingFaceM4/idefics2-8b
+tags:
+- generated_from_trainer
+model-index:
+- name: mantis-8b-idefics2-video-eval-95k-2epoch_4096
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/dongfu/Mantis/runs/825wf4gr)
+# mantis-8b-idefics2-video-eval-95k-2epoch_4096
+
+This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,18 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      32000
+    ],
+    [
+      32001
+    ]
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2,
+    32002
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.41.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:598503ceb550fcc32356ad6cdb5cfd6b839e250ae3b033ff77e0bdb1892a72ef
+size 4966706832

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc5299420d6ef7845a645dbc989e07058d1a006431a3ea6ab25dfeb12f7e8780
+size 4915917232

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e190189f8236c8ff8ea08420096d100d09ca2c376b6322e1fc8fd3158e72a1d
+size 4999820504

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eafbf61af5d51a150ba78fb483e5f515f23c4f5352da2713c23c9243fc1d38bd
+size 1923190976

model.safetensors.index.json

@@ -0,0 +1,770 @@
+{
+  "metadata": {
+    "total_size": 16805536224
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.connector.modality_projection.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.modality_projection.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.modality_projection.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.latents": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.0.input_context_norm.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.0.input_latents_norm.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.1.input_context_norm.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.1.input_latents_norm.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.2.input_context_norm.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.2.input_latents_norm.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.connector.perceiver_resampler.norm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.text_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.text_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.text_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.text_model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors"
+  }
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71aa3ba4613ad17ee7e9b4fc6f359bd4b93b4beba74cc1fe8d941886fe6d7d0a
-size 6456
+oid sha256:bd6322e66469311e2701c82c34b7faee7c3421f7e454577d42a404c23b0e7736
+size 6584