Upload AriaForConditionalGeneration

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 +1,37 @@
+{
+  "architectures": [
+    "AriaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_token_index": 32000,
+  "model_type": "aria",
+  "pad_token_id": 32001,
+  "projector_patch_to_query_dict": {
+    "1225": 128,
+    "4900": 256
+  },
+  "text_config": {
+    "hidden_size": 2560,
+    "intermediate_size": 13568,
+    "max_position_embeddings": 65536,
+    "model_type": "aria_text_model",
+    "moe_intermediate_size": 1664,
+    "moe_num_experts": 64,
+    "moe_topk": 6,
+    "num_attention_heads": 20,
+    "num_experts_per_tok": 6,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 20,
+    "rope_theta": 5000000,
+    "vocab_size": 100416
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "vision_config": {
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "idefics3",
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32001,
+  "transformers_version": "4.46.0.dev0"
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201e6ed888d2b2f66d3f6cec109dbd98e8070e2419147c0db4414b3902243947
+size 4922712808

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e01ad06d26257a8e8db6bc52db3a9fba63bfdf81a082811c6d58dd5c04ee16f
+size 4569849136

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec21b36b156902258a0c0217b3c39a0dd64043d02e000249139411a51993724
+size 4128475752

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab8eb30b71ccbb5c13be1ac48a639dee6997836456d50c132195bf1c26b629b
+size 4569849136

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a59cb471534e8f0649f81de4f4b4cab9247e48e73f25380e4956df49d50fc68
+size 4128475792

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db566f7143d6b4e3a37c69515dc0df8f78230f7c92230d3e3b804cc908cde6f
+size 4569849160

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69756e94c50cb07cae2e1aa9690000de2ae33d013d9b1c5e4532e77308967e35
+size 4128475784

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335585019c0b362663fe00b7beb4a03bc13c02c856757cf01d8af6be97332157
+size 4569849160

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a838a0d5ca56dcf3971f9b0db6b757dc5c98eff7874b40048f9b8c7d655f58d
+size 4128475784

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3936bec75ea6078b36a91bf82106d53a664c59d3afb64599661690dfb460c94a
+size 4569849160

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1ac5302deb2f973154a4c6283c8cf24e9e2df8fda88f0ea2a941552fcaf12b
+size 4128475784

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254829d5cb85a3e25334ac46e4b436e1c45b8b8124db8a2ff9fa956454a6fae9
+size 2201043136

model.safetensors.index.json

@@ -0,0 +1,801 @@
+{
+  "metadata": {
+    "total_size": 50615277792
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.experts.fc1.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.experts.fc2.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.router.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.shared_experts.down_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.shared_experts.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.mlp.shared_experts.up_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.experts.fc1.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.experts.fc2.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.router.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.experts.fc1.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.experts.fc2.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.router.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.shared_experts.down_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.mlp.shared_experts.up_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.experts.fc1.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.experts.fc2.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.router.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.shared_experts.down_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.mlp.shared_experts.up_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.experts.fc1.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.experts.fc2.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.router.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.shared_experts.down_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.mlp.shared_experts.up_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.experts.fc1.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.experts.fc2.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.router.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.shared_experts.down_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.mlp.shared_experts.up_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.experts.fc1.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.experts.fc2.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.router.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.shared_experts.down_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.mlp.shared_experts.up_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.experts.fc1.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.experts.fc2.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.router.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.shared_experts.down_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.mlp.shared_experts.up_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.experts.fc1.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.experts.fc2.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.router.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.shared_experts.down_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.mlp.shared_experts.up_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.experts.fc1.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.experts.fc2.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.router.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.shared_experts.down_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.mlp.shared_experts.up_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.experts.fc1.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.experts.fc2.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.router.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.shared_experts.down_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.mlp.shared_experts.up_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.experts.fc1.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.experts.fc2.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.router.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.shared_experts.down_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.mlp.shared_experts.up_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.experts.fc1.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.experts.fc2.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.router.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.shared_experts.down_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.mlp.shared_experts.up_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.experts.fc1.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.experts.fc2.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.router.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.shared_experts.down_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.mlp.shared_experts.up_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.experts.fc1.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.experts.fc2.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.router.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.shared_experts.down_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.mlp.shared_experts.up_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.experts.fc1.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.experts.fc2.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.router.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.shared_experts.down_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.mlp.shared_experts.up_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.experts.fc1.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.experts.fc2.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.router.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.shared_experts.down_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.mlp.shared_experts.up_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.experts.fc1.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.experts.fc2.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.router.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.shared_experts.down_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.mlp.shared_experts.up_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.experts.fc1.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.experts.fc2.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.router.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.shared_experts.down_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.mlp.shared_experts.up_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.experts.fc1.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.experts.fc2.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.router.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.shared_experts.down_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.mlp.shared_experts.up_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.experts.fc1.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.experts.fc2.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.router.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.shared_experts.down_proj.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.mlp.shared_experts.up_proj.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.experts.fc1.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.experts.fc2.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.router.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.shared_experts.down_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.mlp.shared_experts.up_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.experts.fc1.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.experts.fc2.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.router.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.shared_experts.down_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.mlp.shared_experts.up_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.experts.fc1.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.experts.fc2.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.router.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.shared_experts.down_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.mlp.shared_experts.up_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.experts.fc1.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.experts.fc2.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.router.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.shared_experts.down_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.mlp.shared_experts.up_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.experts.fc1.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.experts.fc2.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.router.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.shared_experts.down_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.mlp.shared_experts.up_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.experts.fc1.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.experts.fc2.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.router.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.shared_experts.down_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.mlp.shared_experts.up_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.experts.fc1.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.experts.fc2.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.router.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.shared_experts.down_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.mlp.shared_experts.up_proj.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "language_model.model.norm.weight": "model-00012-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.layer_norm.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.layer_norm.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.linear.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.linear.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.ln_kv.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.ln_kv.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.multihead_attn.in_proj_bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.multihead_attn.in_proj_weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.multihead_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.multihead_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.cross_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.ffn.linear_in.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.ffn.linear_out.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.ln_ffn.bias": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.ln_ffn.weight": "model-00001-of-00012.safetensors",
+    "multi_modal_projector.query": "model-00001-of-00012.safetensors",
+    "vision_tower.embeddings.patch_embedding.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.embeddings.patch_embedding.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.embeddings.position_embedding.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.layer_norm1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.layer_norm1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.layer_norm2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.layer_norm2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "vision_tower.post_layernorm.bias": "model-00001-of-00012.safetensors",
+    "vision_tower.post_layernorm.weight": "model-00001-of-00012.safetensors"
+  }
+}