Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: vidore/colqwen2-base
+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/colqwen2-base",
+  "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).*$|.*(custom_text_proj).*$)",
+  "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 sha256:424c5a9e63dd020e56b11ef5c9b15aad6b33c9e2e381351752a7a0ab926f42bd
+size 74018232

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 %}"
+}

git_hash.txt

@@ -0,0 +1 @@
+519dc28f01fa839a9d41faa1d7a6e75f1ba2411c

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": "ColQwen2Processor",
+  "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": 0.81055, "ndcg_at_3": 0.85719, "ndcg_at_5": 0.87022, "ndcg_at_10": 0.87667, "ndcg_at_20": 0.88012, "ndcg_at_100": 0.88658, "ndcg_at_1000": 0.88768, "map_at_1": 0.81055, "map_at_3": 0.84505, "map_at_5": 0.85238, "map_at_10": 0.85512, "map_at_20": 0.85606, "map_at_100": 0.85693, "map_at_1000": 0.85699, "recall_at_1": 0.81055, "recall_at_3": 0.89258, "recall_at_5": 0.92383, "recall_at_10": 0.94336, "recall_at_20": 0.95703, "recall_at_100": 0.99219, "recall_at_1000": 1.0, "precision_at_1": 0.81055, "precision_at_3": 0.29753, "precision_at_5": 0.18477, "precision_at_10": 0.09434, "precision_at_20": 0.04785, "precision_at_100": 0.00992, "precision_at_1000": 0.001, "mrr_at_1": 0.80859375, "mrr_at_3": 0.8463541666666664, "mrr_at_5": 0.8522135416666664, "mrr_at_10": 0.8550308469742062, "mrr_at_20": 0.856307368017501, "mrr_at_100": 0.8570664741046659, "mrr_at_1000": 0.8571400935291285, "naucs_at_1_max": 0.3343399328890829, "naucs_at_1_std": -0.09992862824659382, "naucs_at_1_diff1": 0.9236029523512583, "naucs_at_3_max": 0.43183853197760536, "naucs_at_3_std": 0.0751425245683777, "naucs_at_3_diff1": 0.903599549403758, "naucs_at_5_max": 0.46672435600758844, "naucs_at_5_std": 0.23412716556100796, "naucs_at_5_diff1": 0.8971623445062238, "naucs_at_10_max": 0.4687400001833971, "naucs_at_10_std": 0.41359460270505527, "naucs_at_10_diff1": 0.9296138210487797, "naucs_at_20_max": 0.4826174888782515, "naucs_at_20_std": 0.5451765148209757, "naucs_at_20_diff1": 0.9443309311931258, "naucs_at_100_max": 0.31679531417363554, "naucs_at_100_std": 0.589243357096261, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_energy": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.95393, "ndcg_at_5": 0.9578, "ndcg_at_10": 0.9578, "ndcg_at_20": 0.96287, "ndcg_at_100": 0.96287, "ndcg_at_1000": 0.96287, "map_at_1": 0.93, "map_at_3": 0.94833, "map_at_5": 0.95033, "map_at_10": 0.95033, "map_at_20": 0.95173, "map_at_100": 0.95173, "map_at_1000": 0.95173, "recall_at_1": 0.93, "recall_at_3": 0.97, "recall_at_5": 0.98, "recall_at_10": 0.98, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.93, "precision_at_3": 0.32333, "precision_at_5": 0.196, "precision_at_10": 0.098, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.94, "mrr_at_3": 0.9533333333333335, "mrr_at_5": 0.9553333333333334, "mrr_at_10": 0.9564444444444444, "mrr_at_20": 0.9571111111111111, "mrr_at_100": 0.9571111111111111, "mrr_at_1000": 0.9571111111111111, "naucs_at_1_max": 0.6125783646792062, "naucs_at_1_std": -0.5158730158730173, "naucs_at_1_diff1": 0.8336001067093499, "naucs_at_3_max": 0.7152194211017727, "naucs_at_3_std": -0.8249299719887898, "naucs_at_3_diff1": 0.9128540305010931, "naucs_at_5_max": 0.7957516339869297, "naucs_at_5_std": -0.3674136321195164, "naucs_at_5_diff1": 0.9346405228758136, "naucs_at_10_max": 0.7957516339869297, "naucs_at_10_std": -0.3674136321195164, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.95155, "ndcg_at_5": 0.95585, "ndcg_at_10": 0.95942, "ndcg_at_20": 0.95942, "ndcg_at_100": 0.95942, "ndcg_at_1000": 0.95942, "map_at_1": 0.91, "map_at_3": 0.94167, "map_at_5": 0.94417, "map_at_10": 0.94583, "map_at_20": 0.94583, "map_at_100": 0.94583, "map_at_1000": 0.94583, "recall_at_1": 0.91, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.91, "precision_at_3": 0.32667, "precision_at_5": 0.198, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.92, "mrr_at_3": 0.9483333333333335, "mrr_at_5": 0.9508333333333334, "mrr_at_10": 0.9525, "mrr_at_20": 0.9525, "mrr_at_100": 0.9525, "mrr_at_1000": 0.9525, "naucs_at_1_max": 0.5016080506276587, "naucs_at_1_std": -0.22798008092125713, "naucs_at_1_diff1": 0.9400871459694983, "naucs_at_3_max": 0.7222222222222141, "naucs_at_3_std": 0.24042950513538458, "naucs_at_3_diff1": 0.9346405228758099, "naucs_at_5_max": 0.7222222222222276, "naucs_at_5_std": 0.35807656395891135, "naucs_at_5_diff1": 0.8692810457516413, "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_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.97, "ndcg_at_3": 0.98131, "ndcg_at_5": 0.98131, "ndcg_at_10": 0.98432, "ndcg_at_20": 0.98432, "ndcg_at_100": 0.98432, "ndcg_at_1000": 0.98432, "map_at_1": 0.97, "map_at_3": 0.97833, "map_at_5": 0.97833, "map_at_10": 0.97944, "map_at_20": 0.97944, "map_at_100": 0.97944, "map_at_1000": 0.97944, "recall_at_1": 0.97, "recall_at_3": 0.99, "recall_at_5": 0.99, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.97, "precision_at_3": 0.33, "precision_at_5": 0.198, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.97, "mrr_at_3": 0.9783333333333333, "mrr_at_5": 0.9783333333333333, "mrr_at_10": 0.9794444444444445, "mrr_at_20": 0.9794444444444445, "mrr_at_100": 0.9794444444444445, "mrr_at_1000": 0.9794444444444445, "naucs_at_1_max": 0.7642390289449127, "naucs_at_1_std": -0.5634920634920663, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 0.8692810457516356, "naucs_at_3_std": -0.5634920634921204, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 0.8692810457516413, "naucs_at_5_std": -0.5634920634920767, "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_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.83, "ndcg_at_3": 0.91702, "ndcg_at_5": 0.9252, "ndcg_at_10": 0.9252, "ndcg_at_20": 0.9252, "ndcg_at_100": 0.92732, "ndcg_at_1000": 0.92732, "map_at_1": 0.83, "map_at_3": 0.89833, "map_at_5": 0.90283, "map_at_10": 0.90283, "map_at_20": 0.90283, "map_at_100": 0.90323, "map_at_1000": 0.90323, "recall_at_1": 0.83, "recall_at_3": 0.97, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.83, "precision_at_3": 0.32333, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.83, "mrr_at_3": 0.8983333333333333, "mrr_at_5": 0.9028333333333333, "mrr_at_10": 0.9028333333333333, "mrr_at_20": 0.9028333333333333, "mrr_at_100": 0.9032681159420289, "mrr_at_1000": 0.9032681159420289, "naucs_at_1_max": 0.158210947930574, "naucs_at_1_std": 0.11061124978231868, "naucs_at_1_diff1": 0.8998664886515357, "naucs_at_3_max": 0.8513849984438244, "naucs_at_3_std": 0.6591970121381888, "naucs_at_3_diff1": 0.807812013694371, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.5541549953314738, "naucs_at_5_diff1": 0.5541549953314738, "naucs_at_10_max": 1.0, "naucs_at_10_std": 0.5541549953314738, "naucs_at_10_diff1": 0.5541549953314738, "naucs_at_20_max": 1.0, "naucs_at_20_std": 0.5541549953314738, "naucs_at_20_diff1": 0.5541549953314738, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "infovqa_subsampled": {"ndcg_at_1": 0.832, "ndcg_at_3": 0.87459, "ndcg_at_5": 0.88595, "ndcg_at_10": 0.89216, "ndcg_at_20": 0.8956, "ndcg_at_100": 0.89923, "ndcg_at_1000": 0.90155, "map_at_1": 0.832, "map_at_3": 0.865, "map_at_5": 0.8712, "map_at_10": 0.87361, "map_at_20": 0.8745, "map_at_100": 0.87512, "map_at_1000": 0.87521, "recall_at_1": 0.832, "recall_at_3": 0.902, "recall_at_5": 0.93, "recall_at_10": 0.95, "recall_at_20": 0.964, "recall_at_100": 0.982, "recall_at_1000": 1.0, "precision_at_1": 0.832, "precision_at_3": 0.30067, "precision_at_5": 0.186, "precision_at_10": 0.095, "precision_at_20": 0.0482, "precision_at_100": 0.00982, "precision_at_1000": 0.001, "mrr_at_1": 0.834, "mrr_at_3": 0.8639999999999999, "mrr_at_5": 0.8705999999999999, "mrr_at_10": 0.8737023809523807, "mrr_at_20": 0.8746066885728648, "mrr_at_100": 0.8752238268311066, "mrr_at_1000": 0.8753112970433495, "naucs_at_1_max": 0.6373116285620386, "naucs_at_1_std": 0.10029458710858709, "naucs_at_1_diff1": 0.9392634148631519, "naucs_at_3_max": 0.7274147754339835, "naucs_at_3_std": 0.16842927647249306, "naucs_at_3_diff1": 0.880142533203757, "naucs_at_5_max": 0.8866213151927437, "naucs_at_5_std": 0.3796051754034935, "naucs_at_5_diff1": 0.918167266906761, "naucs_at_10_max": 0.8634920634920645, "naucs_at_10_std": 0.28547152194211, "naucs_at_10_diff1": 0.9181139122315616, "naucs_at_20_max": 0.8971625687311942, "naucs_at_20_std": 0.3903413217138755, "naucs_at_20_diff1": 0.9337327523601999, "naucs_at_100_max": 0.9564270152505423, "naucs_at_100_std": 0.7665732959850535, "naucs_at_100_diff1": 0.9564270152505423, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.442, "ndcg_at_3": 0.51095, "ndcg_at_5": 0.54038, "ndcg_at_10": 0.56062, "ndcg_at_20": 0.57229, "ndcg_at_100": 0.59422, "ndcg_at_1000": 0.61263, "map_at_1": 0.442, "map_at_3": 0.494, "map_at_5": 0.5102, "map_at_10": 0.51865, "map_at_20": 0.52188, "map_at_100": 0.52495, "map_at_1000": 0.52567, "recall_at_1": 0.442, "recall_at_3": 0.56, "recall_at_5": 0.632, "recall_at_10": 0.694, "recall_at_20": 0.74, "recall_at_100": 0.858, "recall_at_1000": 1.0, "precision_at_1": 0.442, "precision_at_3": 0.18667, "precision_at_5": 0.1264, "precision_at_10": 0.0694, "precision_at_20": 0.037, "precision_at_100": 0.00858, "precision_at_1000": 0.001, "mrr_at_1": 0.44, "mrr_at_3": 0.4953333333333335, "mrr_at_5": 0.5090333333333336, "mrr_at_10": 0.5182833333333333, "mrr_at_20": 0.5221514120640284, "mrr_at_100": 0.5249686200302078, "mrr_at_1000": 0.5257004927899901, "naucs_at_1_max": 0.41783392577773026, "naucs_at_1_std": 0.4537253478271088, "naucs_at_1_diff1": 0.8660431417922727, "naucs_at_3_max": 0.3653219395866456, "naucs_at_3_std": 0.47488928003633907, "naucs_at_3_diff1": 0.7836106064047238, "naucs_at_5_max": 0.3095958579211595, "naucs_at_5_std": 0.5546541766800461, "naucs_at_5_diff1": 0.7260905670823006, "naucs_at_10_max": 0.20512537751991183, "naucs_at_10_std": 0.5623650444130609, "naucs_at_10_diff1": 0.6905208262928166, "naucs_at_20_max": 0.15354202992579397, "naucs_at_20_std": 0.6416811970317505, "naucs_at_20_diff1": 0.6889988240541748, "naucs_at_100_max": 0.15275440828442793, "naucs_at_100_std": 0.8523481210927357, "naucs_at_100_diff1": 0.6174128944884475, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "arxivqa_subsampled": {"ndcg_at_1": 0.794, "ndcg_at_3": 0.83955, "ndcg_at_5": 0.85117, "ndcg_at_10": 0.86349, "ndcg_at_20": 0.86858, "ndcg_at_100": 0.87555, "ndcg_at_1000": 0.87612, "map_at_1": 0.794, "map_at_3": 0.82833, "map_at_5": 0.83483, "map_at_10": 0.83994, "map_at_20": 0.84135, "map_at_100": 0.84229, "map_at_1000": 0.84232, "recall_at_1": 0.794, "recall_at_3": 0.872, "recall_at_5": 0.9, "recall_at_10": 0.938, "recall_at_20": 0.958, "recall_at_100": 0.996, "recall_at_1000": 1.0, "precision_at_1": 0.794, "precision_at_3": 0.29067, "precision_at_5": 0.18, "precision_at_10": 0.0938, "precision_at_20": 0.0479, "precision_at_100": 0.00996, "precision_at_1000": 0.001, "mrr_at_1": 0.798, "mrr_at_3": 0.8293333333333331, "mrr_at_5": 0.8362333333333332, "mrr_at_10": 0.8409261904761903, "mrr_at_20": 0.8424823580787975, "mrr_at_100": 0.8433074071950472, "mrr_at_1000": 0.843359789652919, "naucs_at_1_max": 0.6915461260196928, "naucs_at_1_std": 0.03234215806406001, "naucs_at_1_diff1": 0.912541922759604, "naucs_at_3_max": 0.75287606632224, "naucs_at_3_std": 0.0863570827826497, "naucs_at_3_diff1": 0.8822164483960117, "naucs_at_5_max": 0.7516246498599451, "naucs_at_5_std": 0.08857142857142664, "naucs_at_5_diff1": 0.8562558356676011, "naucs_at_10_max": 0.7896448902141491, "naucs_at_10_std": 0.1641968615403146, "naucs_at_10_diff1": 0.8670220776482614, "naucs_at_20_max": 0.7843804188341977, "naucs_at_20_std": 0.15337246009514424, "naucs_at_20_diff1": 0.9079631852741096, "naucs_at_100_max": 0.8692810457516423, "naucs_at_100_std": -0.5929038281979426, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.81429, "ndcg_at_3": 0.87279, "ndcg_at_5": 0.88186, "ndcg_at_10": 0.89222, "ndcg_at_20": 0.89757, "ndcg_at_100": 0.90052, "ndcg_at_1000": 0.90052, "map_at_1": 0.81429, "map_at_3": 0.85952, "map_at_5": 0.8647, "map_at_10": 0.86896, "map_at_20": 0.8704, "map_at_100": 0.87092, "map_at_1000": 0.87092, "recall_at_1": 0.81429, "recall_at_3": 0.91071, "recall_at_5": 0.93214, "recall_at_10": 0.96429, "recall_at_20": 0.98571, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.81429, "precision_at_3": 0.30357, "precision_at_5": 0.18643, "precision_at_10": 0.09643, "precision_at_20": 0.04929, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.8214285714285714, "mrr_at_3": 0.8648809523809525, "mrr_at_5": 0.8691666666666668, "mrr_at_10": 0.8738236961451248, "mrr_at_20": 0.8749634853941578, "mrr_at_100": 0.8754808417680698, "mrr_at_1000": 0.8754808417680698, "naucs_at_1_max": 0.4565466636092641, "naucs_at_1_std": 0.1956451119773753, "naucs_at_1_diff1": 0.8674138194603682, "naucs_at_3_max": 0.5534080298786193, "naucs_at_3_std": 0.3311111111111117, "naucs_at_3_diff1": 0.8503454715219424, "naucs_at_5_max": 0.5605189444198757, "naucs_at_5_std": 0.33114649368519294, "naucs_at_5_diff1": 0.8383458646616553, "naucs_at_10_max": 0.6084033613445389, "naucs_at_10_std": 0.5421101774042957, "naucs_at_10_diff1": 0.8622782446311822, "naucs_at_20_max": 0.6091269841269938, "naucs_at_20_std": 0.5764472455649069, "naucs_at_20_diff1": 0.7537348272642382, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.59471, "ndcg_at_3": 0.70326, "ndcg_at_5": 0.72999, "ndcg_at_10": 0.75244, "ndcg_at_20": 0.76271, "ndcg_at_100": 0.76822, "ndcg_at_1000": 0.77066, "map_at_1": 0.59471, "map_at_3": 0.67729, "map_at_5": 0.69211, "map_at_10": 0.70143, "map_at_20": 0.7043, "map_at_100": 0.70506, "map_at_1000": 0.70518, "recall_at_1": 0.59471, "recall_at_3": 0.77811, "recall_at_5": 0.84305, "recall_at_10": 0.91221, "recall_at_20": 0.9525, "recall_at_100": 0.98196, "recall_at_1000": 1.0, "precision_at_1": 0.59471, "precision_at_3": 0.25937, "precision_at_5": 0.16861, "precision_at_10": 0.09122, "precision_at_20": 0.04762, "precision_at_100": 0.00982, "precision_at_1000": 0.001, "mrr_at_1": 0.5874924834636199, "mrr_at_3": 0.6745840849869714, "mrr_at_5": 0.6892563640008025, "mrr_at_10": 0.6982723897336047, "mrr_at_20": 0.7011049205620223, "mrr_at_100": 0.7018840500311513, "mrr_at_1000": 0.7019941826596074, "naucs_at_1_max": 0.12417603736905262, "naucs_at_1_std": -0.29266989910281593, "naucs_at_1_diff1": 0.7646475880480366, "naucs_at_3_max": 0.1429148550840905, "naucs_at_3_std": -0.2955832208142499, "naucs_at_3_diff1": 0.6756220947738238, "naucs_at_5_max": 0.1882616452321695, "naucs_at_5_std": -0.2707062530755226, "naucs_at_5_diff1": 0.6829043338797425, "naucs_at_10_max": 0.2955835422501849, "naucs_at_10_std": -0.060705191429939714, "naucs_at_10_diff1": 0.6550255164412594, "naucs_at_20_max": 0.5083369525641758, "naucs_at_20_std": 0.28366171474864466, "naucs_at_20_diff1": 0.6692612601621288, "naucs_at_100_max": 0.678836018475218, "naucs_at_100_std": 0.6754869495060698, "naucs_at_100_diff1": 0.7266241608428402, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.64, "ndcg_at_3": 0.77095, "ndcg_at_5": 0.78343, "ndcg_at_10": 0.80023, "ndcg_at_20": 0.80538, "ndcg_at_100": 0.80912, "ndcg_at_1000": 0.812, "map_at_1": 0.64, "map_at_3": 0.74, "map_at_5": 0.747, "map_at_10": 0.7543, "map_at_20": 0.75576, "map_at_100": 0.75629, "map_at_1000": 0.75645, "recall_at_1": 0.64, "recall_at_3": 0.86, "recall_at_5": 0.89, "recall_at_10": 0.94, "recall_at_20": 0.96, "recall_at_100": 0.98, "recall_at_1000": 1.0, "precision_at_1": 0.64, "precision_at_3": 0.28667, "precision_at_5": 0.178, "precision_at_10": 0.094, "precision_at_20": 0.048, "precision_at_100": 0.0098, "precision_at_1000": 0.001, "mrr_at_1": 0.64, "mrr_at_3": 0.74, "mrr_at_5": 0.7475, "mrr_at_10": 0.7548015873015872, "mrr_at_20": 0.7563015873015871, "mrr_at_100": 0.7568474930087832, "mrr_at_1000": 0.7570124761737665, "naucs_at_1_max": -0.11647400689743286, "naucs_at_1_std": -0.2506705837271687, "naucs_at_1_diff1": 0.7163111508494064, "naucs_at_3_max": 0.2976652348621302, "naucs_at_3_std": -0.070146875433005, "naucs_at_3_diff1": 0.598067063876957, "naucs_at_5_max": 0.16416115453998784, "naucs_at_5_std": -0.1600807490765389, "naucs_at_5_diff1": 0.7171634739283573, "naucs_at_10_max": -0.03384687208216874, "naucs_at_10_std": -0.2789449112978528, "naucs_at_10_diff1": 0.6763149704326195, "naucs_at_20_max": -0.22000466853407427, "naucs_at_20_std": -0.367063492063485, "naucs_at_20_diff1": 0.625933706816059, "naucs_at_100_max": -1.1517273576097031, "naucs_at_100_std": -1.4458450046685247, "naucs_at_100_diff1": 0.5401493930905731, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_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_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": "ColQwen2Processor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_config.yml

@@ -0,0 +1,43 @@
+config:
+  (): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
+  output_dir: !path ../../../models/colqwen2-multi
+  processor:
+    (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
+    class_to_instanciate: !ext colpali_engine.models.ColQwen2Processor
+    pretrained_model_name_or_path:  "./models/Qwen2-VL-2B-Instruct" # "./models/paligemma-3b-mix-448"
+    # max_length: 50
+
+  model:
+    (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
+    class_to_instanciate: !ext colpali_engine.models.ColQwen2
+    pretrained_model_name_or_path: "./models/colqwen2_base"
+    torch_dtype:  !ext torch.bfloat16
+    use_cache: false
+#    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_detailed
+  eval_dataset_loader: !import ../data/test_data.yaml
+
+  # max_length: 50
+  run_eval: true
+  add_suffix: true
+  loss_func:
+    (): colpali_engine.loss.late_interaction_losses.ColbertPairwiseCELoss
+  tr_args: !import ../tr_args/default_tr_args.yaml
+  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).*$|.*(custom_text_proj).*$)'
+    # target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
+