Add files using upload-large-folder tool

.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/colqwen2.5-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 0.14.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vidore/colqwen2.5-base",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "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:d8a0a2aa5b97160cde30d9fc26874e11f7c9dfce607fd3e2a02c91a09b17e697
+size 239815040

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|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 @@
+67f724577dd70727a08a96a38e7ddb05e3946050

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": "Qwen2_5_VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "ColQwen2_5_Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

results.json

@@ -0,0 +1,588 @@
+{
+    "metadata": {
+        "timestamp": "2025-01-30T14:08:26.760026",
+        "vidore_benchmark_version": "4.0.3.dev20+g2d72668"
+    },
+    "metrics": {
+        "arxivqa_test_subsampled": {
+            "ndcg_at_1": 0.83,
+            "ndcg_at_3": 0.87855,
+            "ndcg_at_5": 0.88517,
+            "ndcg_at_10": 0.8947,
+            "ndcg_at_20": 0.89981,
+            "ndcg_at_50": 0.90189,
+            "ndcg_at_100": 0.90285,
+            "map_at_1": 0.83,
+            "map_at_3": 0.86633,
+            "map_at_5": 0.87003,
+            "map_at_10": 0.87386,
+            "map_at_20": 0.87529,
+            "map_at_50": 0.87566,
+            "map_at_100": 0.87574,
+            "recall_at_1": 0.83,
+            "recall_at_3": 0.914,
+            "recall_at_5": 0.93,
+            "recall_at_10": 0.96,
+            "recall_at_20": 0.98,
+            "recall_at_50": 0.99,
+            "recall_at_100": 0.996,
+            "precision_at_1": 0.83,
+            "precision_at_3": 0.30467,
+            "precision_at_5": 0.186,
+            "precision_at_10": 0.096,
+            "precision_at_20": 0.049,
+            "precision_at_50": 0.0198,
+            "precision_at_100": 0.00996,
+            "mrr_at_1": 0.834,
+            "mrr_at_3": 0.8696666666666666,
+            "mrr_at_5": 0.8724666666666667,
+            "mrr_at_10": 0.8768738095238096,
+            "mrr_at_20": 0.8780439976689977,
+            "mrr_at_50": 0.8784954053717398,
+            "mrr_at_100": 0.8785747821152928,
+            "naucs_at_1_max": 0.7814883612933191,
+            "naucs_at_1_std": -0.014564346665118771,
+            "naucs_at_1_diff1": 0.9431415800777861,
+            "naucs_at_3_max": 0.7651293075369701,
+            "naucs_at_3_std": 0.13162008989642363,
+            "naucs_at_3_diff1": 0.876392417432091,
+            "naucs_at_5_max": 0.7719887955182062,
+            "naucs_at_5_std": 0.12731759370415013,
+            "naucs_at_5_diff1": 0.8762838468720809,
+            "naucs_at_10_max": 0.8234126984126983,
+            "naucs_at_10_std": 0.03160597572361713,
+            "naucs_at_10_diff1": 0.8921568627450972,
+            "naucs_at_20_max": 0.8225957049486448,
+            "naucs_at_20_std": -0.02110177404295123,
+            "naucs_at_20_diff1": 0.9084967320261399,
+            "naucs_at_50_max": 0.9738562091503188,
+            "naucs_at_50_std": 0.3997198879551785,
+            "naucs_at_50_diff1": 0.947712418300658,
+            "naucs_at_100_max": 1.0,
+            "naucs_at_100_std": 1.0,
+            "naucs_at_100_diff1": 0.9346405228758466
+        },
+        "docvqa_test_subsampled": {
+            "ndcg_at_1": 0.5255,
+            "ndcg_at_3": 0.59582,
+            "ndcg_at_5": 0.61852,
+            "ndcg_at_10": 0.6347,
+            "ndcg_at_20": 0.6492,
+            "ndcg_at_50": 0.65706,
+            "ndcg_at_100": 0.66361,
+            "map_at_1": 0.5255,
+            "map_at_3": 0.57871,
+            "map_at_5": 0.59124,
+            "map_at_10": 0.59815,
+            "map_at_20": 0.6021,
+            "map_at_50": 0.60333,
+            "map_at_100": 0.60394,
+            "recall_at_1": 0.5255,
+            "recall_at_3": 0.64523,
+            "recall_at_5": 0.70067,
+            "recall_at_10": 0.74945,
+            "recall_at_20": 0.8071,
+            "recall_at_50": 0.84701,
+            "recall_at_100": 0.88692,
+            "precision_at_1": 0.5255,
+            "precision_at_3": 0.21508,
+            "precision_at_5": 0.14013,
+            "precision_at_10": 0.07494,
+            "precision_at_20": 0.04035,
+            "precision_at_50": 0.01694,
+            "precision_at_100": 0.00887,
+            "mrr_at_1": 0.5254988913525499,
+            "mrr_at_3": 0.5798226164079823,
+            "mrr_at_5": 0.5909090909090909,
+            "mrr_at_10": 0.5981936085594622,
+            "mrr_at_20": 0.6018577072277826,
+            "mrr_at_50": 0.603184631365057,
+            "mrr_at_100": 0.6036950361798563,
+            "naucs_at_1_max": 0.3862474572443775,
+            "naucs_at_1_std": 0.6866980709008784,
+            "naucs_at_1_diff1": 0.908866111398327,
+            "naucs_at_3_max": 0.3232612877463118,
+            "naucs_at_3_std": 0.7754733885431401,
+            "naucs_at_3_diff1": 0.8488934990862631,
+            "naucs_at_5_max": 0.26561580627789727,
+            "naucs_at_5_std": 0.8294969802329596,
+            "naucs_at_5_diff1": 0.843549438877749,
+            "naucs_at_10_max": 0.21226897631460165,
+            "naucs_at_10_std": 0.9004830786766392,
+            "naucs_at_10_diff1": 0.8313389289681655,
+            "naucs_at_20_max": 0.1442628756616487,
+            "naucs_at_20_std": 0.9192991363569017,
+            "naucs_at_20_diff1": 0.8284091873092273,
+            "naucs_at_50_max": 0.04661475790032267,
+            "naucs_at_50_std": 0.9356118889205624,
+            "naucs_at_50_diff1": 0.8459735188892017,
+            "naucs_at_100_max": -0.014764226166713695,
+            "naucs_at_100_std": 0.9484296739649325,
+            "naucs_at_100_diff1": 0.853153345512516
+        },
+        "syntheticDocQA_energy_test": {
+            "ndcg_at_1": 0.95,
+            "ndcg_at_3": 0.96131,
+            "ndcg_at_5": 0.96131,
+            "ndcg_at_10": 0.96487,
+            "ndcg_at_20": 0.96757,
+            "ndcg_at_50": 0.96952,
+            "ndcg_at_100": 0.96952,
+            "map_at_1": 0.95,
+            "map_at_3": 0.95833,
+            "map_at_5": 0.95833,
+            "map_at_10": 0.96,
+            "map_at_20": 0.96083,
+            "map_at_50": 0.96113,
+            "map_at_100": 0.96113,
+            "recall_at_1": 0.95,
+            "recall_at_3": 0.97,
+            "recall_at_5": 0.97,
+            "recall_at_10": 0.98,
+            "recall_at_20": 0.99,
+            "recall_at_50": 1.0,
+            "recall_at_100": 1.0,
+            "precision_at_1": 0.95,
+            "precision_at_3": 0.32333,
+            "precision_at_5": 0.194,
+            "precision_at_10": 0.098,
+            "precision_at_20": 0.0495,
+            "precision_at_50": 0.02,
+            "precision_at_100": 0.01,
+            "mrr_at_1": 0.95,
+            "mrr_at_3": 0.9583333333333333,
+            "mrr_at_5": 0.9603333333333333,
+            "mrr_at_10": 0.9603333333333333,
+            "mrr_at_20": 0.9612424242424242,
+            "mrr_at_50": 0.9615549242424243,
+            "mrr_at_100": 0.9615549242424243,
+            "naucs_at_1_max": 0.5612511671335213,
+            "naucs_at_1_std": -0.8497665732959815,
+            "naucs_at_1_diff1": 0.9477124183006508,
+            "naucs_at_3_max": 0.807812013694371,
+            "naucs_at_3_std": -0.6484593837535022,
+            "naucs_at_3_diff1": 0.9564270152505466,
+            "naucs_at_5_max": 0.807812013694364,
+            "naucs_at_5_std": -0.6484593837535011,
+            "naucs_at_5_diff1": 0.9564270152505424,
+            "naucs_at_10_max": 0.9346405228758136,
+            "naucs_at_10_std": -0.10270774976657283,
+            "naucs_at_10_diff1": 0.9346405228758136,
+            "naucs_at_20_max": 0.8692810457516413,
+            "naucs_at_20_std": -0.5634920634920767,
+            "naucs_at_20_diff1": 1.0,
+            "naucs_at_50_max": null,
+            "naucs_at_50_std": null,
+            "naucs_at_50_diff1": null,
+            "naucs_at_100_max": null,
+            "naucs_at_100_std": null,
+            "naucs_at_100_diff1": null
+        },
+        "tatdqa_test": {
+            "ndcg_at_1": 0.69502,
+            "ndcg_at_3": 0.78919,
+            "ndcg_at_5": 0.80833,
+            "ndcg_at_10": 0.82129,
+            "ndcg_at_20": 0.82519,
+            "ndcg_at_50": 0.82963,
+            "ndcg_at_100": 0.83159,
+            "map_at_1": 0.69502,
+            "map_at_3": 0.76701,
+            "map_at_5": 0.77755,
+            "map_at_10": 0.78302,
+            "map_at_20": 0.7842,
+            "map_at_50": 0.78491,
+            "map_at_100": 0.78508,
+            "recall_at_1": 0.69502,
+            "recall_at_3": 0.85298,
+            "recall_at_5": 0.89976,
+            "recall_at_10": 0.93925,
+            "recall_at_20": 0.95383,
+            "recall_at_50": 0.97631,
+            "recall_at_100": 0.98846,
+            "precision_at_1": 0.69502,
+            "precision_at_3": 0.28433,
+            "precision_at_5": 0.17995,
+            "precision_at_10": 0.09392,
+            "precision_at_20": 0.04769,
+            "precision_at_50": 0.01953,
+            "precision_at_100": 0.00988,
+            "mrr_at_1": 0.6950182260024301,
+            "mrr_at_3": 0.7656946132037261,
+            "mrr_at_5": 0.7770554880518429,
+            "mrr_at_10": 0.7827320681208895,
+            "mrr_at_20": 0.783837406855329,
+            "mrr_at_50": 0.784510459247072,
+            "mrr_at_100": 0.7846961562032659,
+            "naucs_at_1_max": 0.2747145592665206,
+            "naucs_at_1_std": -0.09557716491043182,
+            "naucs_at_1_diff1": 0.8084384046681937,
+            "naucs_at_3_max": 0.3330280541363154,
+            "naucs_at_3_std": -0.0389562599865292,
+            "naucs_at_3_diff1": 0.7240601862039753,
+            "naucs_at_5_max": 0.352919194006459,
+            "naucs_at_5_std": 0.0514244344972758,
+            "naucs_at_5_diff1": 0.6583624352004738,
+            "naucs_at_10_max": 0.43229730811413347,
+            "naucs_at_10_std": 0.2815741957749473,
+            "naucs_at_10_diff1": 0.6007108794001051,
+            "naucs_at_20_max": 0.4241317350379727,
+            "naucs_at_20_std": 0.2971486230084223,
+            "naucs_at_20_diff1": 0.5874614197126973,
+            "naucs_at_50_max": 0.5140385840003181,
+            "naucs_at_50_std": 0.518664544400799,
+            "naucs_at_50_diff1": 0.5976629425860989,
+            "naucs_at_100_max": 0.4955447990957944,
+            "naucs_at_100_std": 0.5556756488737464,
+            "naucs_at_100_diff1": 0.6696787538618733
+        },
+        "infovqa_test_subsampled": {
+            "ndcg_at_1": 0.88664,
+            "ndcg_at_3": 0.91826,
+            "ndcg_at_5": 0.92479,
+            "ndcg_at_10": 0.93028,
+            "ndcg_at_20": 0.93185,
+            "ndcg_at_50": 0.93365,
+            "ndcg_at_100": 0.93435,
+            "map_at_1": 0.88664,
+            "map_at_3": 0.91093,
+            "map_at_5": 0.91447,
+            "map_at_10": 0.91689,
+            "map_at_20": 0.91735,
+            "map_at_50": 0.91756,
+            "map_at_100": 0.91763,
+            "recall_at_1": 0.88664,
+            "recall_at_3": 0.93927,
+            "recall_at_5": 0.95547,
+            "recall_at_10": 0.97166,
+            "recall_at_20": 0.97773,
+            "recall_at_50": 0.98785,
+            "recall_at_100": 0.9919,
+            "precision_at_1": 0.88664,
+            "precision_at_3": 0.31309,
+            "precision_at_5": 0.19109,
+            "precision_at_10": 0.09717,
+            "precision_at_20": 0.04889,
+            "precision_at_50": 0.01976,
+            "precision_at_100": 0.00992,
+            "mrr_at_1": 0.8846153846153846,
+            "mrr_at_3": 0.9092442645074225,
+            "mrr_at_5": 0.9127867746288799,
+            "mrr_at_10": 0.9150801683696421,
+            "mrr_at_20": 0.9155341004025214,
+            "mrr_at_50": 0.9157652608527469,
+            "mrr_at_100": 0.9158356239262059,
+            "naucs_at_1_max": 0.6077965938527005,
+            "naucs_at_1_std": -0.034859963613718514,
+            "naucs_at_1_diff1": 0.9382491207886892,
+            "naucs_at_3_max": 0.7083430308645834,
+            "naucs_at_3_std": 0.09173878193665044,
+            "naucs_at_3_diff1": 0.941058293792039,
+            "naucs_at_5_max": 0.828261285914772,
+            "naucs_at_5_std": 0.25360809635439513,
+            "naucs_at_5_diff1": 0.9374342352707031,
+            "naucs_at_10_max": 0.8969865162710334,
+            "naucs_at_10_std": 0.5367916133086486,
+            "naucs_at_10_diff1": 0.9521757785748344,
+            "naucs_at_20_max": 0.927259949634811,
+            "naucs_at_20_std": 0.6312197158498455,
+            "naucs_at_20_diff1": 0.9643814216187027,
+            "naucs_at_50_max": 0.9129323639568211,
+            "naucs_at_50_std": 0.5625809313845725,
+            "naucs_at_50_diff1": 0.9564661819783937,
+            "naucs_at_100_max": 0.9346992729676393,
+            "naucs_at_100_std": 0.7480140525249407,
+            "naucs_at_100_diff1": 0.9673496364838197
+        },
+        "syntheticDocQA_healthcare_industry_test": {
+            "ndcg_at_1": 0.97,
+            "ndcg_at_3": 0.98762,
+            "ndcg_at_5": 0.98762,
+            "ndcg_at_10": 0.98762,
+            "ndcg_at_20": 0.98762,
+            "ndcg_at_50": 0.98762,
+            "ndcg_at_100": 0.98762,
+            "map_at_1": 0.97,
+            "map_at_3": 0.98333,
+            "map_at_5": 0.98333,
+            "map_at_10": 0.98333,
+            "map_at_20": 0.98333,
+            "map_at_50": 0.98333,
+            "map_at_100": 0.98333,
+            "recall_at_1": 0.97,
+            "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": 0.97,
+            "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": 0.97,
+            "mrr_at_3": 0.9833333333333333,
+            "mrr_at_5": 0.9833333333333333,
+            "mrr_at_10": 0.9833333333333333,
+            "mrr_at_20": 0.9833333333333333,
+            "mrr_at_50": 0.9833333333333333,
+            "mrr_at_100": 0.9833333333333333,
+            "naucs_at_1_max": 0.8202614379084989,
+            "naucs_at_1_std": -0.2198879551820713,
+            "naucs_at_1_diff1": 0.9564270152505465,
+            "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": null,
+            "naucs_at_50_std": null,
+            "naucs_at_50_diff1": null,
+            "naucs_at_100_max": null,
+            "naucs_at_100_std": null,
+            "naucs_at_100_diff1": null
+        },
+        "tabfquad_test_subsampled": {
+            "ndcg_at_1": 0.83571,
+            "ndcg_at_3": 0.88699,
+            "ndcg_at_5": 0.89851,
+            "ndcg_at_10": 0.90549,
+            "ndcg_at_20": 0.91018,
+            "ndcg_at_50": 0.9125,
+            "ndcg_at_100": 0.9125,
+            "map_at_1": 0.83571,
+            "map_at_3": 0.875,
+            "map_at_5": 0.88125,
+            "map_at_10": 0.88416,
+            "map_at_20": 0.88553,
+            "map_at_50": 0.88598,
+            "map_at_100": 0.88598,
+            "recall_at_1": 0.83571,
+            "recall_at_3": 0.92143,
+            "recall_at_5": 0.95,
+            "recall_at_10": 0.97143,
+            "recall_at_20": 0.98929,
+            "recall_at_50": 1.0,
+            "recall_at_100": 1.0,
+            "precision_at_1": 0.83571,
+            "precision_at_3": 0.30714,
+            "precision_at_5": 0.19,
+            "precision_at_10": 0.09714,
+            "precision_at_20": 0.04946,
+            "precision_at_50": 0.02,
+            "precision_at_100": 0.01,
+            "mrr_at_1": 0.8392857142857143,
+            "mrr_at_3": 0.8767857142857143,
+            "mrr_at_5": 0.8830357142857143,
+            "mrr_at_10": 0.8858517573696145,
+            "mrr_at_20": 0.8872690305726021,
+            "mrr_at_50": 0.8877252707609851,
+            "mrr_at_100": 0.8877252707609851,
+            "naucs_at_1_max": 0.4880524536858767,
+            "naucs_at_1_std": 0.1966050571171859,
+            "naucs_at_1_diff1": 0.9065802421597565,
+            "naucs_at_3_max": 0.5683515830574649,
+            "naucs_at_3_std": 0.33952975129445734,
+            "naucs_at_3_diff1": 0.8935786435786452,
+            "naucs_at_5_max": 0.7507669734560504,
+            "naucs_at_5_std": 0.5118714152327615,
+            "naucs_at_5_diff1": 0.9109643857543043,
+            "naucs_at_10_max": 0.8150093370681609,
+            "naucs_at_10_std": 0.5556722689075682,
+            "naucs_at_10_diff1": 0.934640522875815,
+            "naucs_at_20_max": 0.9128540305011011,
+            "naucs_at_20_std": 0.807812013694365,
+            "naucs_at_20_diff1": 0.9564270152505505,
+            "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
+        },
+        "syntheticDocQA_government_reports_test": {
+            "ndcg_at_1": 0.91,
+            "ndcg_at_3": 0.94393,
+            "ndcg_at_5": 0.95254,
+            "ndcg_at_10": 0.9561,
+            "ndcg_at_20": 0.9561,
+            "ndcg_at_50": 0.9561,
+            "ndcg_at_100": 0.9561,
+            "map_at_1": 0.91,
+            "map_at_3": 0.935,
+            "map_at_5": 0.94,
+            "map_at_10": 0.94167,
+            "map_at_20": 0.94167,
+            "map_at_50": 0.94167,
+            "map_at_100": 0.94167,
+            "recall_at_1": 0.91,
+            "recall_at_3": 0.97,
+            "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": 0.91,
+            "precision_at_3": 0.32333,
+            "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": 0.91,
+            "mrr_at_3": 0.9383333333333332,
+            "mrr_at_5": 0.9428333333333333,
+            "mrr_at_10": 0.9428333333333333,
+            "mrr_at_20": 0.9428333333333333,
+            "mrr_at_50": 0.9428333333333333,
+            "mrr_at_100": 0.9428333333333333,
+            "naucs_at_1_max": 0.8246706089843343,
+            "naucs_at_1_std": 0.4518103537711367,
+            "naucs_at_1_diff1": 0.9564270152505436,
+            "naucs_at_3_max": 0.7027699968876487,
+            "naucs_at_3_std": 0.460939931528168,
+            "naucs_at_3_diff1": 0.9564270152505466,
+            "naucs_at_5_max": 0.5541549953314738,
+            "naucs_at_5_std": -0.1713352007469681,
+            "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": null,
+            "naucs_at_50_std": null,
+            "naucs_at_50_diff1": null,
+            "naucs_at_100_max": null,
+            "naucs_at_100_std": null,
+            "naucs_at_100_diff1": null
+        },
+        "shiftproject_test": {
+            "ndcg_at_1": 0.73,
+            "ndcg_at_3": 0.85095,
+            "ndcg_at_5": 0.85526,
+            "ndcg_at_10": 0.86174,
+            "ndcg_at_20": 0.86703,
+            "ndcg_at_50": 0.87134,
+            "ndcg_at_100": 0.87134,
+            "map_at_1": 0.73,
+            "map_at_3": 0.82333,
+            "map_at_5": 0.82583,
+            "map_at_10": 0.82851,
+            "map_at_20": 0.83009,
+            "map_at_50": 0.83092,
+            "map_at_100": 0.83092,
+            "recall_at_1": 0.73,
+            "recall_at_3": 0.93,
+            "recall_at_5": 0.94,
+            "recall_at_10": 0.96,
+            "recall_at_20": 0.98,
+            "recall_at_50": 1.0,
+            "recall_at_100": 1.0,
+            "precision_at_1": 0.73,
+            "precision_at_3": 0.31,
+            "precision_at_5": 0.188,
+            "precision_at_10": 0.096,
+            "precision_at_20": 0.049,
+            "precision_at_50": 0.02,
+            "precision_at_100": 0.01,
+            "mrr_at_1": 0.75,
+            "mrr_at_3": 0.8316666666666667,
+            "mrr_at_5": 0.8341666666666667,
+            "mrr_at_10": 0.8380238095238096,
+            "mrr_at_20": 0.8386904761904762,
+            "mrr_at_50": 0.8395600414078674,
+            "mrr_at_100": 0.8395600414078674,
+            "naucs_at_1_max": -0.0662092826672433,
+            "naucs_at_1_std": -0.3356071477717276,
+            "naucs_at_1_diff1": 0.7686999941024986,
+            "naucs_at_3_max": -0.05822328931572497,
+            "naucs_at_3_std": -0.2665732959850601,
+            "naucs_at_3_diff1": 0.7789782579698524,
+            "naucs_at_5_max": 0.22206660441954526,
+            "naucs_at_5_std": -0.33146591970121353,
+            "naucs_at_5_diff1": 0.8883442265795238,
+            "naucs_at_10_max": 0.05240429505135564,
+            "naucs_at_10_std": -0.4458450046685252,
+            "naucs_at_10_diff1": 0.8651960784313721,
+            "naucs_at_20_max": -0.5088702147525547,
+            "naucs_at_20_std": -0.5929038281979383,
+            "naucs_at_20_diff1": 0.9346405228758136,
+            "naucs_at_50_max": null,
+            "naucs_at_50_std": null,
+            "naucs_at_50_diff1": null,
+            "naucs_at_100_max": null,
+            "naucs_at_100_std": null,
+            "naucs_at_100_diff1": null
+        },
+        "syntheticDocQA_artificial_intelligence_test": {
+            "ndcg_at_1": 0.98,
+            "ndcg_at_3": 0.99262,
+            "ndcg_at_5": 0.99262,
+            "ndcg_at_10": 0.99262,
+            "ndcg_at_20": 0.99262,
+            "ndcg_at_50": 0.99262,
+            "ndcg_at_100": 0.99262,
+            "map_at_1": 0.98,
+            "map_at_3": 0.99,
+            "map_at_5": 0.99,
+            "map_at_10": 0.99,
+            "map_at_20": 0.99,
+            "map_at_50": 0.99,
+            "map_at_100": 0.99,
+            "recall_at_1": 0.98,
+            "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": 0.98,
+            "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": 0.98,
+            "mrr_at_3": 0.99,
+            "mrr_at_5": 0.99,
+            "mrr_at_10": 0.99,
+            "mrr_at_20": 0.99,
+            "mrr_at_50": 0.99,
+            "mrr_at_100": 0.99,
+            "naucs_at_1_max": 0.3489729225023353,
+            "naucs_at_1_std": -0.2987861811391249,
+            "naucs_at_1_diff1": 1.0,
+            "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": null,
+            "naucs_at_50_std": null,
+            "naucs_at_50_diff1": null,
+            "naucs_at_100_max": null,
+            "naucs_at_100_std": null,
+            "naucs_at_100_diff1": null
+        }
+    }
+}

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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "ColQwen2_5_Processor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_config.yml

@@ -0,0 +1,72 @@
+config:
+  (): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
+  output_dir: !path ../../../models/colqwen2_5_train
+  processor:
+    (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
+    class_to_instanciate: !ext colpali_engine.models.ColQwen2_5_Processor
+    pretrained_model_name_or_path:  "./models/ColQwen2.5-VL-3B-Instruct" # "./models/paligemma-3b-mix-448"
+    # num_image_tokens: 2048
+    # max_length: 50
+
+  model:
+    (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
+    class_to_instanciate: !ext colpali_engine.models.ColQwen2_5
+    pretrained_model_name_or_path: "./models/ColQwen2.5-VL-3B-Instruct"
+    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.late_interaction_losses.ColbertPairwiseCELoss
+  tr_args:
+    (): transformers.training_args.TrainingArguments
+    output_dir: null
+    overwrite_output_dir: true
+    num_train_epochs: 3
+    per_device_train_batch_size: 32
+    gradient_checkpointing: true
+    gradient_checkpointing_kwargs: { "use_reentrant": false }
+    # gradient_checkpointing: true
+    # 6 x 8 gpus = 48 batch size
+    # gradient_accumulation_steps: 4
+    per_device_eval_batch_size: 16
+    eval_strategy: "steps"
+    dataloader_num_workers: 8
+    # bf16: true
+    save_steps: 500
+    logging_steps: 10
+    eval_steps: 100
+    warmup_steps: 500
+    learning_rate: 1e-4
+    save_total_limit: 1
+    # resume_from_checkpoint: true
+    # optim: "paged_adamw_8bit"
+    # wandb logging
+    # wandb_project: "colqwen2"
+    # run_name: "colqwen2-ba32-nolora"
+    report_to: "wandb"
+
+
+  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).*$|.*(custom_text_proj).*$)'
+