Upload Llamavision

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "Llamavision"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_llamavision.LlamavisionConfig",
+    "AutoModelForCausalLM": "modeling_llamavision.Llamavision"
+  },
+  "model_type": "llamavision",
+  "text_config": {
+    "_name_or_path": "unsloth/llama-3-8b-Instruct",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "bos_token_id": 128000,
+    "eos_token_id": 128001,
+    "intermediate_size": 14336,
+    "max_length": 8192,
+    "max_position_embeddings": 8192,
+    "model_type": "llama",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 500000.0,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 128256
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.1",
+  "vision_config": {
+    "_name_or_path": "google/siglip-so400m-patch14-384",
+    "hidden_size": 1152,
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  }
+}

configuration_llamavision.py

@@ -0,0 +1,10 @@
+from transformers import PretrainedConfig, LlamaConfig, SiglipVisionConfig
+
+
+class LlamavisionConfig(PretrainedConfig):
+    model_type = "llamavision"
+
+    def __init__(self, **kwargs):
+        self.text_config = LlamaConfig(**kwargs.pop("text_config", {}))
+        self.vision_config = SiglipVisionConfig(**kwargs.pop("vision_config", {}))
+        super().__init__(**kwargs)

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714aef0cdd97d1169b28366b091f255d0efd17aef2c12864e6f39225f95731c1
+size 4976699488

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bb4d0a7469bd10363261c1b912d5ac1d377a5585705422bcdc9030a04ba1b3
+size 4999803760

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff55ff1d011e233001606c5a81b4e40806b62f18b4bb06e718488dad96c5aa88
+size 4915917176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17eb367214434a3136473281972d065d4fc4762380ccaf45a2d199f16c0118c
+size 2067659728

model.safetensors.index.json

@@ -0,0 +1,750 @@
+{
+  "metadata": {
+    "total_size": 16959981696
+  },
+  "weight_map": {
+    "mm_projector.model.0.bias": "model-00004-of-00004.safetensors",
+    "mm_projector.model.0.weight": "model-00004-of-00004.safetensors",
+    "mm_projector.model.2.bias": "model-00004-of-00004.safetensors",
+    "mm_projector.model.2.weight": "model-00004-of-00004.safetensors",
+    "text_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "text_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "text_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "text_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "text_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "text_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "text_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "text_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.embeddings.patch_embedding.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.embeddings.patch_embedding.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.embeddings.position_embedding.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.attention.in_proj_bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.attention.in_proj_weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.attention.out_proj.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.attention.out_proj.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.layernorm.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.layernorm.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.head.probe": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
+    "vision_model.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
+  }
+}

modeling_llamavision.py

@@ -0,0 +1,147 @@
+import torch
+import torch.nn as nn
+from transformers import (
+    PreTrainedModel,
+    AutoModelForCausalLM,
+    AutoModel,
+    SiglipImageProcessor,
+)
+from .configuration_llamavision import LlamavisionConfig
+
+
+class ProjectionModule(nn.Module):
+    def __init__(self, mm_hidden_size=1152, hidden_size=4096):
+        super(ProjectionModule, self).__init__()
+
+        # Directly set up the sequential model
+        self.model = nn.Sequential(
+            nn.Linear(mm_hidden_size, hidden_size),
+            nn.GELU(),
+            nn.Linear(hidden_size, hidden_size),
+        )
+
+    def forward(self, x):
+        return self.model(x)
+
+
+class Llamavision(PreTrainedModel):
+    config_class = LlamavisionConfig
+
+    def __init__(self, config):
+        super().__init__(config)
+
+        self.text_model = AutoModelForCausalLM.from_config(config.text_config)
+        self.vision_model = AutoModel.from_config(config.vision_config)
+        self.processor = SiglipImageProcessor()
+        self.mm_projector = ProjectionModule()
+
+    @property
+    def device(self):
+        return self.text_model.device
+
+    def tokenizer_image_token(
+        self, prompt, tokenizer, image_token_index=-200, return_tensors=None
+    ):
+        prompt_chunks = [
+            tokenizer(chunk).input_ids for chunk in prompt.split("<image>")
+        ]
+
+        def insert_separator(X, sep):
+            return [ele for sublist in zip(X, [sep] * len(X)) for ele in sublist][:-1]
+
+        input_ids = []
+        offset = 0
+        if (
+            len(prompt_chunks) > 0
+            and len(prompt_chunks[0]) > 0
+            and prompt_chunks[0][0] == tokenizer.bos_token_id
+        ):
+            offset = 1
+            input_ids.append(prompt_chunks[0][0])
+
+        for x in insert_separator(prompt_chunks, [image_token_index] * (offset + 1)):
+            input_ids.extend(x[offset:])
+
+        return torch.tensor(input_ids, dtype=torch.long)
+
+    def process_tensors(self, input_ids, image_features, embedding_layer):
+        # Find the index of -200 in input_ids
+        split_index = (input_ids == -200).nonzero(as_tuple=True)[1][0]
+
+        # Split the input_ids at the index found, excluding -200
+        input_ids_1 = input_ids[:, :split_index]
+        input_ids_2 = input_ids[:, split_index + 1 :]
+
+        # Convert input_ids to embeddings
+        embeddings_1 = embedding_layer(input_ids_1)
+        embeddings_2 = embedding_layer(input_ids_2)
+
+        device = image_features.device
+        token_embeddings_part1 = embeddings_1.to(device)
+        token_embeddings_part2 = embeddings_2.to(device)
+
+        # Concatenate the token embeddings and image features
+        concatenated_embeddings = torch.cat(
+            [token_embeddings_part1, image_features, token_embeddings_part2], dim=1
+        )
+
+        # Create the corrected attention mask
+        attention_mask = torch.ones(
+            concatenated_embeddings.shape[:2], dtype=torch.long, device=device
+        )
+        return concatenated_embeddings, attention_mask
+
+    def answer_question(self, image, question, tokenizer, **kwargs):
+        question = "<image>" + question
+
+        prompt = f"<|start_header_id|>user<|end_header_id|>\n\n{question}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
+
+        input_ids = (
+            self.tokenizer_image_token(prompt, tokenizer, -200, return_tensors="pt")
+            .unsqueeze(0)
+            .to(self.device)
+        )
+        terminators = [
+            tokenizer.eos_token_id,
+            tokenizer.convert_tokens_to_ids("<|eot_id|>"),
+        ]
+        with torch.inference_mode():
+            image_inputs = self.processor(
+                images=[image],
+                return_tensors="pt",
+                do_resize=True,
+                size={"height": 384, "width": 384},
+            )
+
+            image_inputs = image_inputs["pixel_values"].to(
+                device=self.device, dtype=self.dtype
+            )
+
+            image_forward_outs = self.vision_model(
+                image_inputs,
+                output_hidden_states=True,
+            )
+
+            image_features = image_forward_outs.hidden_states[-2]
+
+            projected_embeddings = self.mm_projector(image_features).to(self.device)
+
+            embedding_layer = self.text_model.get_input_embeddings()
+            # text_embeddings = embedding_layer(input_ids)
+
+            new_embeds, attn_mask = self.process_tensors(
+                input_ids, projected_embeddings, embedding_layer
+            )
+
+            attn_mask = attn_mask.to(self.device)
+            new_embeds = new_embeds.to(self.device)
+            answer = self.text_model.generate(
+                inputs_embeds=new_embeds,
+                attention_mask=attn_mask,
+                eos_token_id=terminators,
+                temperature=0.2,
+                do_sample=True,
+                **kwargs,
+            )[0]
+
+            return answer