Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: vidore/qwen2-warmup
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vidore/qwen2-warmup",
+  "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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$)",
+  "task_type": "FEATURE_EXTRACTION",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a61e7b4b5f7f1344c51c9562e42028fc6a5d249b13b01f295ed671f020afba0
+size 73911504

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-1/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ./models/qwen2-warmup
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-1/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./models/qwen2-warmup",
+  "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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$)",
+  "task_type": "FEATURE_EXTRACTION",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a61e7b4b5f7f1344c51c9562e42028fc6a5d249b13b01f295ed671f020afba0
+size 73911504

checkpoint-1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:262a8ad7b3402e214a46606348ff96b81b1b6b7a5c0c80a2c63c3f45b83c52f4
+size 148047722

checkpoint-1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bc4796bc3e0dc59d9e0321c222ccc99ad65a21ac1d0c1042bef1b4f98dc7b2
+size 14244

checkpoint-1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5063320b2ed5be9b12c1f1e888ba81d5f641af39e744b6d69d0fe9f434e8fa
+size 1064

checkpoint-1/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0021645021645021645,
+  "eval_steps": 100,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 10,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2408329788063744.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660edb4f2e8aa8ef5d8b37930392b365a74c52d9193fc363b720fe54b17eb3ca
+size 5176

git_hash.txt

@@ -0,0 +1 @@
+6ae20d9016361cdaafd4eea7d089b116e62a29d2

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "BiQwen2Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

results.json

@@ -0,0 +1 @@
+{"validation_set": {"ndcg_at_1": 0.796, "ndcg_at_3": 0.85495, "ndcg_at_5": 0.8639, "ndcg_at_10": 0.87254, "ndcg_at_20": 0.8799, "ndcg_at_50": 0.88348, "ndcg_at_100": 0.88382, "map_at_1": 0.796, "map_at_3": 0.84133, "map_at_5": 0.84623, "map_at_10": 0.84994, "map_at_20": 0.85185, "map_at_50": 0.85242, "map_at_100": 0.85246, "recall_at_1": 0.796, "recall_at_3": 0.894, "recall_at_5": 0.916, "recall_at_10": 0.942, "recall_at_20": 0.972, "recall_at_50": 0.99, "recall_at_100": 0.992, "precision_at_1": 0.796, "precision_at_3": 0.298, "precision_at_5": 0.1832, "precision_at_10": 0.0942, "precision_at_20": 0.0486, "precision_at_50": 0.0198, "precision_at_100": 0.00992, "mrr_at_1": 0.796, "mrr_at_3": 0.843, "mrr_at_5": 0.8469, "mrr_at_10": 0.8505325396825396, "mrr_at_20": 0.8521482558635035, "mrr_at_50": 0.8528272330920051, "mrr_at_100": 0.85286113139709, "naucs_at_1_max": 0.12337304593347541, "naucs_at_1_std": -0.7591714462797723, "naucs_at_1_diff1": 0.9149015711235945, "naucs_at_3_max": -0.012867614433025963, "naucs_at_3_std": -0.9498251779280444, "naucs_at_3_diff1": 0.8684397351933689, "naucs_at_5_max": -0.014372415632921569, "naucs_at_5_std": -0.8904117202436561, "naucs_at_5_diff1": 0.8718932017251367, "naucs_at_10_max": -0.03784732283718035, "naucs_at_10_std": -0.9889565021410871, "naucs_at_10_diff1": 0.8798254934157582, "naucs_at_20_max": 0.08703481392556274, "naucs_at_20_std": -0.838368680805674, "naucs_at_20_diff1": 0.8572762438308682, "naucs_at_50_max": -0.2536881419234251, "naucs_at_50_std": -0.956676003734828, "naucs_at_50_diff1": 0.9183006535947666, "naucs_at_100_max": -0.17623716153129299, "naucs_at_100_std": -0.7608543417366961, "naucs_at_100_diff1": 0.9305555555555584}, "syntheticDocQA_energy": {"ndcg_at_1": 0.87, "ndcg_at_3": 0.91917, "ndcg_at_5": 0.92734, "ndcg_at_10": 0.92734, "ndcg_at_20": 0.93276, "ndcg_at_50": 0.93494, "ndcg_at_100": 0.93494, "map_at_1": 0.87, "map_at_3": 0.90833, "map_at_5": 0.91283, "map_at_10": 0.91283, "map_at_20": 0.91451, "map_at_50": 0.91495, "map_at_100": 0.91495, "recall_at_1": 0.87, "recall_at_3": 0.95, "recall_at_5": 0.97, "recall_at_10": 0.97, "recall_at_20": 0.99, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.87, "precision_at_3": 0.31667, "precision_at_5": 0.194, "precision_at_10": 0.097, "precision_at_20": 0.0495, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.87, "mrr_at_3": 0.9083333333333333, "mrr_at_5": 0.9128333333333333, "mrr_at_10": 0.9139444444444444, "mrr_at_20": 0.9147777777777777, "mrr_at_50": 0.9152323232323232, "mrr_at_100": 0.9152323232323232, "naucs_at_1_max": 0.43582907502036694, "naucs_at_1_std": -0.2828630674664893, "naucs_at_1_diff1": 0.8985410649485305, "naucs_at_3_max": 0.13706816059757365, "naucs_at_3_std": -0.7007469654528471, "naucs_at_3_diff1": 0.9183006535947692, "naucs_at_5_max": -0.3020541549953327, "naucs_at_5_std": -0.7268907563025226, "naucs_at_5_diff1": 0.9074074074074108, "naucs_at_10_max": -0.3020541549953327, "naucs_at_10_std": -0.7268907563025226, "naucs_at_10_diff1": 0.9074074074074108, "naucs_at_20_max": -0.1713352007469681, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.97286, "ndcg_at_5": 0.97286, "ndcg_at_10": 0.97286, "ndcg_at_20": 0.97286, "ndcg_at_50": 0.97286, "ndcg_at_100": 0.97286, "map_at_1": 0.93, "map_at_3": 0.96333, "map_at_5": 0.96333, "map_at_10": 0.96333, "map_at_20": 0.96333, "map_at_50": 0.96333, "map_at_100": 0.96333, "recall_at_1": 0.93, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.93, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.94, "mrr_at_3": 0.9683333333333333, "mrr_at_5": 0.9683333333333333, "mrr_at_10": 0.9683333333333333, "mrr_at_20": 0.9683333333333333, "mrr_at_50": 0.9683333333333333, "mrr_at_100": 0.9683333333333333, "naucs_at_1_max": 0.6639322395624917, "naucs_at_1_std": 0.057823129251700287, "naucs_at_1_diff1": 0.943977591036415, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.96655, "ndcg_at_5": 0.96655, "ndcg_at_10": 0.96655, "ndcg_at_20": 0.96655, "ndcg_at_50": 0.96655, "ndcg_at_100": 0.96655, "map_at_1": 0.92, "map_at_3": 0.955, "map_at_5": 0.955, "map_at_10": 0.955, "map_at_20": 0.955, "map_at_50": 0.955, "map_at_100": 0.955, "recall_at_1": 0.92, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.92, "mrr_at_3": 0.955, "mrr_at_5": 0.955, "mrr_at_10": 0.955, "mrr_at_20": 0.955, "mrr_at_50": 0.955, "mrr_at_100": 0.955, "naucs_at_1_max": 0.37511671335200736, "naucs_at_1_std": -0.2263655462184869, "naucs_at_1_diff1": 0.9509803921568633, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.96024, "ndcg_at_5": 0.96454, "ndcg_at_10": 0.96755, "ndcg_at_20": 0.96755, "ndcg_at_50": 0.96755, "ndcg_at_100": 0.96755, "map_at_1": 0.93, "map_at_3": 0.95333, "map_at_5": 0.95583, "map_at_10": 0.95694, "map_at_20": 0.95694, "map_at_50": 0.95694, "map_at_100": 0.95694, "recall_at_1": 0.93, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.93, "precision_at_3": 0.32667, "precision_at_5": 0.198, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.93, "mrr_at_3": 0.9533333333333333, "mrr_at_5": 0.9558333333333333, "mrr_at_10": 0.9570833333333333, "mrr_at_20": 0.9570833333333333, "mrr_at_50": 0.9570833333333333, "mrr_at_100": 0.9570833333333333, "naucs_at_1_max": 0.49593170601574016, "naucs_at_1_std": -0.1608643457382955, "naucs_at_1_diff1": 0.9229691876750709, "naucs_at_3_max": 0.4561157796451816, "naucs_at_3_std": -0.661531279178345, "naucs_at_3_diff1": 0.8611111111111119, "naucs_at_5_max": 0.35807656395891135, "naucs_at_5_std": -1.1517273576097316, "naucs_at_5_diff1": 0.7222222222222276, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "infovqa_subsampled": {"ndcg_at_1": 0.81, "ndcg_at_3": 0.85307, "ndcg_at_5": 0.86873, "ndcg_at_10": 0.87921, "ndcg_at_20": 0.88229, "ndcg_at_50": 0.88317, "ndcg_at_100": 0.88512, "map_at_1": 0.81, "map_at_3": 0.843, "map_at_5": 0.8517, "map_at_10": 0.85609, "map_at_20": 0.85695, "map_at_50": 0.85714, "map_at_100": 0.85731, "recall_at_1": 0.81, "recall_at_3": 0.882, "recall_at_5": 0.92, "recall_at_10": 0.952, "recall_at_20": 0.964, "recall_at_50": 0.968, "recall_at_100": 0.98, "precision_at_1": 0.81, "precision_at_3": 0.294, "precision_at_5": 0.184, "precision_at_10": 0.0952, "precision_at_20": 0.0482, "precision_at_50": 0.01936, "precision_at_100": 0.0098, "mrr_at_1": 0.806, "mrr_at_3": 0.8413333333333334, "mrr_at_5": 0.8497333333333333, "mrr_at_10": 0.8544809523809525, "mrr_at_20": 0.8553121794871795, "mrr_at_50": 0.8554983266733267, "mrr_at_100": 0.8556658414885311, "naucs_at_1_max": 0.141154591649641, "naucs_at_1_std": -0.07635811200167668, "naucs_at_1_diff1": 0.8810571533343818, "naucs_at_3_max": 0.07860614574755015, "naucs_at_3_std": -0.13010867283501834, "naucs_at_3_diff1": 0.8522905262477993, "naucs_at_5_max": 0.2155112044817942, "naucs_at_5_std": 0.259243697478991, "naucs_at_5_diff1": 0.833158263305322, "naucs_at_10_max": 0.17501167133520013, "naucs_at_10_std": 0.5606520385932124, "naucs_at_10_diff1": 0.8140367258014324, "naucs_at_20_max": 0.04276895943562585, "naucs_at_20_std": 0.7092800082996177, "naucs_at_20_diff1": 0.8242815644776446, "naucs_at_50_max": 0.06576797385620768, "naucs_at_50_std": 0.8523576097105556, "naucs_at_50_diff1": 0.8104866946778694, "naucs_at_100_max": 0.17852474323061385, "naucs_at_100_std": 0.8818860877684281, "naucs_at_100_diff1": 0.8921568627450945}, "docvqa_subsampled": {"ndcg_at_1": 0.41, "ndcg_at_3": 0.49335, "ndcg_at_5": 0.51229, "ndcg_at_10": 0.5322, "ndcg_at_20": 0.54738, "ndcg_at_50": 0.56385, "ndcg_at_100": 0.5746, "map_at_1": 0.41, "map_at_3": 0.47367, "map_at_5": 0.48417, "map_at_10": 0.4923, "map_at_20": 0.49649, "map_at_50": 0.49905, "map_at_100": 0.50001, "recall_at_1": 0.41, "recall_at_3": 0.55, "recall_at_5": 0.596, "recall_at_10": 0.658, "recall_at_20": 0.718, "recall_at_50": 0.802, "recall_at_100": 0.868, "precision_at_1": 0.41, "precision_at_3": 0.18333, "precision_at_5": 0.1192, "precision_at_10": 0.0658, "precision_at_20": 0.0359, "precision_at_50": 0.01604, "precision_at_100": 0.00868, "mrr_at_1": 0.41, "mrr_at_3": 0.4726666666666667, "mrr_at_5": 0.48296666666666666, "mrr_at_10": 0.4917436507936508, "mrr_at_20": 0.4959952597969626, "mrr_at_50": 0.4985024962861558, "mrr_at_100": 0.4994159027267983, "naucs_at_1_max": -0.4636449358667992, "naucs_at_1_std": -0.164126742188408, "naucs_at_1_diff1": 0.8276011728690081, "naucs_at_3_max": -0.537999017061012, "naucs_at_3_std": -0.1264452713613703, "naucs_at_3_diff1": 0.741461770694376, "naucs_at_5_max": -0.561941176122966, "naucs_at_5_std": -0.10844064130672434, "naucs_at_5_diff1": 0.7018768799825076, "naucs_at_10_max": -0.5871388568387022, "naucs_at_10_std": -0.07507678269752781, "naucs_at_10_diff1": 0.6741801856008889, "naucs_at_20_max": -0.6113258505388312, "naucs_at_20_std": 0.039377605480469854, "naucs_at_20_diff1": 0.6472060904232113, "naucs_at_50_max": -0.5296614869566092, "naucs_at_50_std": 0.27499016829856143, "naucs_at_50_diff1": 0.6249684881364131, "naucs_at_100_max": -0.645501563276161, "naucs_at_100_std": 0.3408453379306334, "naucs_at_100_diff1": 0.5860021038482894}, "arxivqa_subsampled": {"ndcg_at_1": 0.754, "ndcg_at_3": 0.82374, "ndcg_at_5": 0.83295, "ndcg_at_10": 0.84664, "ndcg_at_20": 0.85383, "ndcg_at_50": 0.85702, "ndcg_at_100": 0.85905, "map_at_1": 0.754, "map_at_3": 0.807, "map_at_5": 0.8122, "map_at_10": 0.81754, "map_at_20": 0.81957, "map_at_50": 0.82009, "map_at_100": 0.82029, "recall_at_1": 0.754, "recall_at_3": 0.872, "recall_at_5": 0.894, "recall_at_10": 0.938, "recall_at_20": 0.966, "recall_at_50": 0.982, "recall_at_100": 0.994, "precision_at_1": 0.754, "precision_at_3": 0.29067, "precision_at_5": 0.1788, "precision_at_10": 0.0938, "precision_at_20": 0.0483, "precision_at_50": 0.01964, "precision_at_100": 0.00994, "mrr_at_1": 0.756, "mrr_at_3": 0.808, "mrr_at_5": 0.8135, "mrr_at_10": 0.8190404761904762, "mrr_at_20": 0.821144196446828, "mrr_at_50": 0.8216980992057245, "mrr_at_100": 0.8218573901238074, "naucs_at_1_max": 0.1428444191856007, "naucs_at_1_std": -0.43192199541099513, "naucs_at_1_diff1": 0.9350541392224136, "naucs_at_3_max": 0.0768953502342892, "naucs_at_3_std": -0.5499294124714647, "naucs_at_3_diff1": 0.8804893067403577, "naucs_at_5_max": 0.05632465434925257, "naucs_at_5_std": -0.48102692437392636, "naucs_at_5_diff1": 0.8673304580870743, "naucs_at_10_max": -0.09901810186440438, "naucs_at_10_std": -0.5959308454564681, "naucs_at_10_diff1": 0.8651396042287877, "naucs_at_20_max": -0.023672213983635542, "naucs_at_20_std": -0.5235349041577391, "naucs_at_20_diff1": 0.894957983193281, "naucs_at_50_max": -0.19664902998236666, "naucs_at_50_std": -0.1808278867102445, "naucs_at_50_diff1": 0.865649963689171, "naucs_at_100_max": -0.9556489262372053, "naucs_at_100_std": 0.14285714285712342, "naucs_at_100_diff1": 0.8692810457516253}, "tabfquad_subsampled": {"ndcg_at_1": 0.88571, "ndcg_at_3": 0.93699, "ndcg_at_5": 0.93699, "ndcg_at_10": 0.94051, "ndcg_at_20": 0.94331, "ndcg_at_50": 0.94405, "ndcg_at_100": 0.94466, "map_at_1": 0.88571, "map_at_3": 0.925, "map_at_5": 0.925, "map_at_10": 0.92649, "map_at_20": 0.9273, "map_at_50": 0.92743, "map_at_100": 0.92749, "recall_at_1": 0.88571, "recall_at_3": 0.97143, "recall_at_5": 0.97143, "recall_at_10": 0.98214, "recall_at_20": 0.99286, "recall_at_50": 0.99643, "recall_at_100": 1.0, "precision_at_1": 0.88571, "precision_at_3": 0.32381, "precision_at_5": 0.19429, "precision_at_10": 0.09821, "precision_at_20": 0.04964, "precision_at_50": 0.01993, "precision_at_100": 0.01, "mrr_at_1": 0.8857142857142857, "mrr_at_3": 0.9255952380952381, "mrr_at_5": 0.9255952380952381, "mrr_at_10": 0.9270833333333333, "mrr_at_20": 0.9279336734693877, "mrr_at_50": 0.9280659486016629, "mrr_at_100": 0.9281264812893142, "naucs_at_1_max": 0.6374288087327964, "naucs_at_1_std": 0.12283459895586181, "naucs_at_1_diff1": 0.8410803274798299, "naucs_at_3_max": 0.8978758169934691, "naucs_at_3_std": 0.2625466853408014, "naucs_at_3_diff1": 0.8631535947712446, "naucs_at_5_max": 0.8978758169934646, "naucs_at_5_std": 0.26254668534080566, "naucs_at_5_diff1": 0.8631535947712403, "naucs_at_10_max": 0.9183006535947714, "naucs_at_10_std": 0.314752567693746, "naucs_at_10_diff1": 0.8071895424836623, "naucs_at_20_max": 0.8611111111111035, "naucs_at_20_std": 0.8611111111111035, "naucs_at_20_diff1": 0.8611111111111035, "naucs_at_50_max": 1.0, "naucs_at_50_std": 1.0, "naucs_at_50_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0}, "tatdqa": {"ndcg_at_1": 0.52977, "ndcg_at_3": 0.64311, "ndcg_at_5": 0.67365, "ndcg_at_10": 0.70159, "ndcg_at_20": 0.71447, "ndcg_at_50": 0.72263, "ndcg_at_100": 0.72448, "map_at_1": 0.52977, "map_at_3": 0.61535, "map_at_5": 0.63234, "map_at_10": 0.64407, "map_at_20": 0.64766, "map_at_50": 0.64904, "map_at_100": 0.6492, "recall_at_1": 0.52977, "recall_at_3": 0.72339, "recall_at_5": 0.79735, "recall_at_10": 0.88274, "recall_at_20": 0.93325, "recall_at_50": 0.97354, "recall_at_100": 0.98497, "precision_at_1": 0.52977, "precision_at_3": 0.24113, "precision_at_5": 0.15947, "precision_at_10": 0.08827, "precision_at_20": 0.04666, "precision_at_50": 0.01947, "precision_at_100": 0.00985, "mrr_at_1": 0.5279615153337343, "mrr_at_3": 0.6150531168570856, "mrr_at_5": 0.6313189015834837, "mrr_at_10": 0.6434737374605083, "mrr_at_20": 0.6468848430310473, "mrr_at_50": 0.6482633204782727, "mrr_at_100": 0.6484247424510643, "naucs_at_1_max": -0.006443992420677248, "naucs_at_1_std": -0.18218281794726, "naucs_at_1_diff1": 0.7055457414361879, "naucs_at_3_max": -0.050556539227135475, "naucs_at_3_std": -0.17760630819242695, "naucs_at_3_diff1": 0.6162068297024225, "naucs_at_5_max": -0.019222306216811074, "naucs_at_5_std": -0.10747978499063429, "naucs_at_5_diff1": 0.5849707721609257, "naucs_at_10_max": 0.09621599533046171, "naucs_at_10_std": 0.058637070424872303, "naucs_at_10_diff1": 0.5587252535330388, "naucs_at_20_max": 0.11158948785105664, "naucs_at_20_std": 0.2009836323027148, "naucs_at_20_diff1": 0.5618909216838407, "naucs_at_50_max": 0.1088579108612422, "naucs_at_50_std": 0.7402223975810361, "naucs_at_50_diff1": 0.6047747365371076, "naucs_at_100_max": -0.049397070807442954, "naucs_at_100_std": 0.8340111571777812, "naucs_at_100_diff1": 0.6156531134683879}, "shift_project": {"ndcg_at_1": 0.67, "ndcg_at_3": 0.77464, "ndcg_at_5": 0.82325, "ndcg_at_10": 0.82997, "ndcg_at_20": 0.82997, "ndcg_at_50": 0.83393, "ndcg_at_100": 0.83393, "map_at_1": 0.67, "map_at_3": 0.75167, "map_at_5": 0.77817, "map_at_10": 0.78108, "map_at_20": 0.78108, "map_at_50": 0.78171, "map_at_100": 0.78171, "recall_at_1": 0.67, "recall_at_3": 0.84, "recall_at_5": 0.96, "recall_at_10": 0.98, "recall_at_20": 0.98, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.67, "precision_at_3": 0.28, "precision_at_5": 0.192, "precision_at_10": 0.098, "precision_at_20": 0.049, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.66, "mrr_at_3": 0.75, "mrr_at_5": 0.773, "mrr_at_10": 0.7775833333333334, "mrr_at_20": 0.7775833333333334, "mrr_at_50": 0.778210113960114, "mrr_at_100": 0.778210113960114, "naucs_at_1_max": 0.32210390885544504, "naucs_at_1_std": -0.3513568417666881, "naucs_at_1_diff1": 0.6506068967852247, "naucs_at_3_max": 0.4938328424153158, "naucs_at_3_std": -0.3930412371134031, "naucs_at_3_diff1": 0.6315660284732447, "naucs_at_5_max": 0.658613445378152, "naucs_at_5_std": 0.2685574229691903, "naucs_at_5_diff1": 0.658613445378152, "naucs_at_10_max": 0.861111111111116, "naucs_at_10_std": -0.024276377217554025, "naucs_at_10_diff1": 0.540149393090577, "naucs_at_20_max": 0.861111111111116, "naucs_at_20_std": -0.024276377217554025, "naucs_at_20_diff1": 0.540149393090577, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "BiQwen2Processor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_config.yml

@@ -0,0 +1,66 @@
+config:
+  (): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
+  output_dir: !path ../../../models/biqwen2-warmup-256-newpad-0e
+  processor:
+    (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
+    class_to_instanciate: !ext colpali_engine.models.BiQwen2Processor
+    pretrained_model_name_or_path:  "./models/colqwen2_base" # "./models/paligemma-3b-mix-448"
+    # max_length: 50
+
+  model:
+    (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
+    class_to_instanciate: !ext colpali_engine.models.BiQwen2
+    pretrained_model_name_or_path: "./models/qwen2-warmup"
+    torch_dtype:  !ext torch.bfloat16
+    use_cache: false
+    attn_implementation: "flash_attention_2"
+#    device_map: "auto"
+#    quantization_config:
+#      (): transformers.BitsAndBytesConfig
+#      load_in_4bit: true
+#      bnb_4bit_quant_type: "nf4"
+#      bnb_4bit_compute_dtype:  "bfloat16"
+#      bnb_4bit_use_double_quant: true
+
+  dataset_loading_func: !ext colpali_engine.utils.dataset_transformation.load_train_set
+  eval_dataset_loader: !import ../data/test_data.yaml
+
+  # max_length: 50
+  run_eval: true
+  
+  loss_func:
+    (): colpali_engine.loss.bi_encoder_losses.BiPairwiseCELoss
+  tr_args:
+    (): transformers.training_args.TrainingArguments
+    output_dir: null
+    overwrite_output_dir: true
+    num_train_epochs: 1
+    per_device_train_batch_size: 64
+    gradient_checkpointing: true
+    gradient_checkpointing_kwargs: { "use_reentrant": false }
+    # 6 x 8 gpus = 48 batch size
+    # gradient_accumulation_steps: 4
+    per_device_eval_batch_size: 64
+    eval_strategy: "steps"
+    dataloader_num_workers: 8
+    # bf16: true
+    save_steps: 500
+    logging_steps: 10
+    max_steps: 1
+    eval_steps: 100
+    warmup_steps: 100
+    learning_rate: 5e-5
+    save_total_limit: 1
+    resume_from_checkpoint: false
+    # optim: "paged_adamw_8bit"
+  peft_config:
+    (): peft.LoraConfig
+    r: 32
+    lora_alpha: 32
+    lora_dropout: 0.1
+    init_lora_weights: "gaussian"
+    bias: "none"
+    task_type: "FEATURE_EXTRACTION"
+    target_modules: '(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$)'
+    # target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
+