Model save

README.md

@@ -0,0 +1,54 @@
+---
+library_name: transformers
+license: gemma
+base_model: google/paligemma-3b-pt-224
+tags:
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: phrivi-finetuned
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# phrivi-finetuned
+
+This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on the generator dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 1
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "google/paligemma-3b-pt-224",
+  "_vocab_size": 257216,
+  "architectures": [
+    "PaliGemmaForConditionalGeneration"
+  ],
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "hidden_size": 2048,
+  "image_token_index": 257152,
+  "model_type": "paligemma",
+  "pad_token_id": 0,
+  "projection_dim": 2048,
+  "text_config": {
+    "hidden_size": 2048,
+    "intermediate_size": 16384,
+    "model_type": "gemma",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 18,
+    "num_image_tokens": 256,
+    "num_key_value_heads": 1,
+    "torch_dtype": "float32",
+    "vocab_size": 257216
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "vision_config": {
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "num_image_tokens": 256,
+    "patch_size": 14,
+    "projection_dim": 2048,
+    "projector_hidden_act": "gelu_fast",
+    "vision_use_head": false
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.47.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc47acb52c0253f018140091ca464469387e7f4f673d8b1663e309c9251614f
+size 4948870952

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27cb649607d6f5eb96c4c90956f1224963f5d46c0680b50ccf82286b046f35ec
+size 421549968

model.safetensors.index.json

@@ -0,0 +1,323 @@
+{
+  "metadata": {
+    "total_size": 5370383360
+  },
+  "weight_map": {
+    "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+    "multi_modal_projector.linear.bias": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.linear.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.cls_token": "model-00001-of-00002.safetensors",
+    "vision_tower.norm.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.pos_embed": "model-00001-of-00002.safetensors"
+  }
+}

runs/Jan09_16-54-11_ac8a8c748630/events.out.tfevents.1736441658.ac8a8c748630.360.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae4d8c54586c1f9bbaf37a95130e810f8e107736a98767352b2f12f6e645fbd
+size 4184

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907e0b6f4af3fc957c0bf305064b8969910f4924b187a6012a3d86231d4fdc13
+size 5304