selimc/turkish-colpali

README.md

@@ -0,0 +1,57 @@
+---
+library_name: peft
+license: gemma
+base_model: vidore/colpali-v1.3-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: turkish-colpali
+  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. -->
+
+# turkish-colpali
+
+This model is a fine-tuned version of [vidore/colpali-v1.3-hf](https://huggingface.co/vidore/colpali-v1.3-hf) on the None 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 100
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.48.0.dev0
+- Pytorch 2.4.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "ColPaliForRetrieval",
+    "parent_library": "transformers.models.colpali.modeling_colpali"
+  },
+  "base_model_name_or_path": "vidore/colpali-v1.3-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6805638cce57f8771f21977e7f6a8b8f1be18e1074d9e5def3a0f3d4190472af
+size 45260040

runs/Jan04_16-53-31_b89e9b3e6935/events.out.tfevents.1736009614.b89e9b3e6935

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94304e03768a97536820befd00e60c5e142f0e5ca75b480d39b5587d15e2df4b
+size 11000

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ea2bc28243b67188a826fd86552b9c1d8c4e7e08a40f98198e8ccbd14281e9
+size 5304