PreFLMR_ViT-G / model.safetensors.index.json
LinWeizheDragon's picture
Upload folder using huggingface_hub
2668634 verified
{
"metadata": {
"total_size": 8338279936
},
"weight_map": {
"context_text_encoder.bert_model.embeddings.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.embeddings.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.embeddings.position_embeddings.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.embeddings.token_type_embeddings.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.embeddings.word_embeddings.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.0.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.1.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.10.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.11.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.2.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.3.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.4.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.5.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.6.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.7.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.8.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.attention.self.key.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.attention.self.key.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.attention.self.query.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.attention.self.query.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.attention.self.value.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.attention.self.value.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.output.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.encoder.layer.9.output.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.pooler.dense.bias": "model-00001-of-00002.safetensors",
"context_text_encoder.bert_model.pooler.dense.weight": "model-00001-of-00002.safetensors",
"context_text_encoder_linear.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.embeddings.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.embeddings.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.embeddings.position_embeddings.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.embeddings.token_type_embeddings.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.embeddings.word_embeddings.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.0.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.1.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.10.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.11.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.2.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.3.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.4.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.5.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.6.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.7.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.8.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.attention.self.key.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.attention.self.key.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.attention.self.query.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.attention.self.query.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.attention.self.value.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.attention.self.value.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.output.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.encoder.layer.9.output.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.pooler.dense.bias": "model-00001-of-00002.safetensors",
"query_text_encoder.bert_model.pooler.dense.weight": "model-00001-of-00002.safetensors",
"query_text_encoder_linear.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.40.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.layer_norm1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.layer_norm1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.layer_norm2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.layer_norm2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.pre_layrnorm.bias": "model-00001-of-00002.safetensors",
"query_vision_encoder.vision_model.vision_model.pre_layrnorm.weight": "model-00001-of-00002.safetensors",
"query_vision_projection.model.0.bias": "model-00002-of-00002.safetensors",
"query_vision_projection.model.0.weight": "model-00002-of-00002.safetensors",
"query_vision_projection.model.2.bias": "model-00002-of-00002.safetensors",
"query_vision_projection.model.2.weight": "model-00002-of-00002.safetensors",
"transformer_mapping_input_linear.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_input_linear.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.attention.self.key.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.attention.self.key.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.attention.self.query.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.attention.self.query.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.attention.self.value.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.attention.self.value.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.crossattention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.crossattention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.crossattention.output.dense.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.crossattention.output.dense.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.crossattention.self.key.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.crossattention.self.key.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.crossattention.self.query.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.crossattention.self.query.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.crossattention.self.value.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.crossattention.self.value.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.intermediate.dense.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.intermediate.dense.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.output.dense.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_network.layer.0.output.dense.weight": "model-00001-of-00002.safetensors",
"transformer_mapping_output_linear.bias": "model-00001-of-00002.safetensors",
"transformer_mapping_output_linear.weight": "model-00001-of-00002.safetensors"
}
}