Mantis-VL/llava_siglip_llama3_8b_finetune_8192
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Mantis-VL/llava_siglip_llama3_8b_finetune_8192
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-25 00:18:50 +08:00
commit ea7f568636
14 changed files with 413638 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

57
README.md Normal file
View File

@@ -0,0 +1,57 @@
---
base_model: MFuyu/llava_siglip_llama3_8b_pretrain_8192
tags:
- generated_from_trainer
model-index:
- name: llava_siglip_llama3_8b_finetune_8192
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# llava_siglip_llama3_8b_finetune_8192
This model is a fine-tuned version of [MFuyu/llava_siglip_llama3_8b_pretrain_8192](https://huggingface.co/MFuyu/llava_siglip_llama3_8b_pretrain_8192) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1.0
### Training results
### Framework versions
- Transformers 4.39.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2

43
config.json Normal file
View File

@@ -0,0 +1,43 @@
{
"_name_or_path": "MFuyu/llava_siglip_llama3_8b_pretrain_8192",
"architectures": [
"LlavaForConditionalGeneration"
],
"ignore_index": -100,
"image_token_index": 128256,
"model_type": "llava",
"pad_token_id": 128257,
"projector_hidden_act": "gelu",
"text_config": {
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 128000,
"eos_token_id": 128001,
"intermediate_size": 14336,
"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": 128258
},
"torch_dtype": "bfloat16",
"transformers_version": "4.39.2",
"vision_config": {
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"image_size": 384,
"intermediate_size": 4304,
"layer_norm_eps": 1e-06,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"patch_size": 14
},
"vision_feature_layer": -2,
"vision_feature_select_strategy": "default",
"vocab_size": 128258
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 128000,
"eos_token_id": 128001,
"pad_token_id": 128257,
"transformers_version": "4.39.2"
}

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1eb2c44b431c009f4f16bef0f55fc037abfad8547a43dcb81607d74db52dc434
size 4886330032

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d6e54f4adf494c1ba70519af7f66e146fc1a1708eb52e2632f32509a3a3adbbc
size 4999820904

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b5052d4d2e8de8138be7d119a5efbe2520cf34ff87708bc17da363d59b4da8f7
size 4915917680

3
model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dca9a32c2e27e1cd1b1b4a675b8e0c4011bfd68c32dae5622b0548b2148d5dfb
size 2158046280

750
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,750 @@
{
"metadata": {
"total_size": 16960014464
},
"weight_map": {
"language_model.lm_head.weight": "model-00004-of-00004.safetensors",
"language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"language_model.model.norm.weight": "model-00004-of-00004.safetensors",
"multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
"multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
"multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
"multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.attention.in_proj_bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.attention.in_proj_weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.attention.out_proj.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.attention.out_proj.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.layernorm.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.layernorm.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.head.probe": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors"
}
}

37
preprocessor_config.json Normal file
View File

@@ -0,0 +1,37 @@
{
"_valid_processor_keys": [
"images",
"do_resize",
"size",
"resample",
"do_rescale",
"rescale_factor",
"do_normalize",
"image_mean",
"image_std",
"return_tensors",
"data_format",
"input_data_format"
],
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.5,
0.5,
0.5
],
"image_processor_type": "SiglipImageProcessor",
"image_std": [
0.5,
0.5,
0.5
],
"processor_class": "MLlavaProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"height": 384,
"width": 384
}
}

21
special_tokens_map.json Normal file
View File

@@ -0,0 +1,21 @@
{
"additional_special_tokens": [
"<image>",
"<|pad|>"
],
"bos_token": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": "<unk>"
}

410578
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

2095
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24089c5ab7a2f2796b48c8aaf15f9207f76287e9c8c6cfe7ce31731e3fbb330c
size 6392