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 +1,126 @@
+---
+license: mit
+datasets:
+- openbmb/VisRAG-Ret-Train-Synthetic-data
+- openbmb/VisRAG-Ret-Train-In-domain-data
+- tsystems/vqa_de_en_batch1
+- vidore/colpali_train_set
+- llamaindex/vdr-multilingual-train
+- Metric-AI/tabfquad_train_set
+language:
+- en
+- fr
+- es
+- it
+- de
+base_model:
+- Qwen/Qwen2.5-VL-3B-Instruct
+tags:
+- vidore
+- multimodal_embedding
+- multilingual_embedding
+- Text-to-Visual Document (T→VD) retrieval
+library_name: peft
+pipeline_tag: visual-document-retrieval
+---
+# ColQwen2.5-3b-multilingual-v1.0: Multilingual Visual Retriever based on Qwen2.5-VL-3B-Instruct with ColBERT strategy
+
+### This is the base version trained on 8xH100 80GB with per_device_batch_size=128 for 8 epoch. 
+
+ColQwen is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features.
+It is a [Qwen2.5-VL-3B](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) extension that generates [ColBERT](https://arxiv.org/abs/2004.12832)- style multi-vector representations of text and images. 
+It was introduced in the paper [ColPali: Efficient Document Retrieval with Vision Language Models](https://arxiv.org/abs/2407.01449) and first released in [this repository](https://github.com/ManuelFay/colpali)
+
+<p align="center"><img width=800 src="https://github.com/illuin-tech/colpali/blob/main/assets/colpali_architecture.webp?raw=true"/></p>
+
+## Version specificity
+This model takes dynamic image resolutions in input and does not resize them, changing their aspect ratio as in ColPali.
+Maximal resolution is set so that 768 image patches are created at most. Experiments show clear improvements with larger amounts of image patches, at the cost of memory requirements.
+
+This version is trained with `colpali-engine==0.3.9`.
+
+## Data
+- **German & English**: Taken from the `tsystems/vqa_de_en_batch1` dataset.
+- **Multilingual dataset**: Taken from `llamaindex/vdr-multilingual-train`.
+- **Synthetic data**: Taken from `openbmb/VisRAG-Ret-Train-Synthetic-data` dataset.  
+- **In-domain VQA dataset**: Taken from `openbmb/VisRAG-Ret-Train-In-domain-data` dataset.
+- **Colpali dataset**: Taken from `vidore/colpali_train_set`.
+
+## Model Training
+
+### Parameters
+We train models  use low-rank adapters ([LoRA](https://arxiv.org/abs/2106.09685)) 
+with `alpha=128`  and `r=128` on the transformer layers from the language model, 
+as well as the final randomly initialized projection layer, and use a `paged_adamw_8bit` optimizer. 
+We train on an 8xH100 GPU setup with distributed data parallelism (via accelerate), a learning rate of 2e-4 with linear decay with 1% warmup steps, batch size per device is 128 in `bfloat16` format
+
+## Installation
+```bash
+pip install git+https://github.com/illuin-tech/colpali
+pip install transformers==4.49.0
+pip install flash-attn --no-build-isolation
+```
+## Usage
+
+```python
+import torch
+from PIL import Image
+
+from colpali_engine.models import ColQwen2_5, ColQwen2_5_Processor
+
+model = ColQwen2_5.from_pretrained(
+        "tsystems/colqwen2.5-3b-multilingual-v1.0",
+        torch_dtype=torch.bfloat16,
+        device_map="cuda:0",  # or "mps" if on Apple Silicon
+    ).eval()
+processor = ColQwen2_5_Processor.from_pretrained("tsystems/colqwen2.5-3b-multilingual-v1.0")
+
+# Your inputs
+images = [
+    Image.new("RGB", (32, 32), color="white"),
+    Image.new("RGB", (16, 16), color="black"),
+]
+queries = [
+    "Is attention really all you need?",
+    "What is the amount of bananas farmed in Salvador?",
+]
+
+# Process the inputs
+batch_images = processor.process_images(images).to(model.device)
+batch_queries = processor.process_queries(queries).to(model.device)
+
+# Forward pass
+with torch.no_grad():
+    image_embeddings = model(**batch_images)
+    query_embeddings = model(**batch_queries)
+
+scores = processor.score_multi_vector(query_embeddings, image_embeddings)
+```
+
+
+## Limitations
+
+ - **Focus**: The model primarily focuses on PDF-type documents and high-ressources languages, potentially limiting its generalization to other document types or less represented languages.
+ - **Support**: The model relies on multi-vector retreiving derived from the ColBERT late interaction mechanism, which may require engineering efforts to adapt to widely used vector retrieval frameworks that lack native multi-vector support.
+
+## License
+
+ColQwen2.5's vision language backbone model (Qwen2.5-VL) is under `apache2.0` license. The adapters attached to the model are under MIT license.
+
+
+## Citation
+
+If you use this models from this organization in your research, please cite the original paper as follows:
+
+```bibtex
+@misc{faysse2024colpaliefficientdocumentretrieval,
+  title={ColPali: Efficient Document Retrieval with Vision Language Models}, 
+  author={Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and Céline Hudelot and Pierre Colombo},
+  year={2024},
+  eprint={2407.01449},
+  archivePrefix={arXiv},
+  primaryClass={cs.IR},
+  url={https://arxiv.org/abs/2407.01449}, 
+}
+```
+- **Developed by:** [T-Systems International](https://www.t-systems.com/de/en)

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/pv_rwm_models/llm/ColQwen25-3B-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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "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 sha256:0c26583c535a9e42ff7f795d2adaa1c6fd64f991c7dadfccb31d7757d1427e12
+size 959057112

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 %}"
+}

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": 602112,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "ColQwen2_5_Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "max_num_visual_tokens": 768,
+  "processor_class": "ColQwen2_5_Processor"
+}

results.json

@@ -0,0 +1,588 @@
+{
+    "metadata": {
+        "timestamp": "2025-03-09T16:34:55.435464",
+        "vidore_benchmark_version": "0.1.dev293+g9358cf6"
+    },
+    "metrics": {
+        "vidore/arxivqa_test_subsampled": {
+            "ndcg_at_1": 0.896,
+            "ndcg_at_3": 0.9285,
+            "ndcg_at_5": 0.93409,
+            "ndcg_at_10": 0.93887,
+            "ndcg_at_20": 0.94191,
+            "ndcg_at_50": 0.94277,
+            "ndcg_at_100": 0.94346,
+            "map_at_1": 0.896,
+            "map_at_3": 0.921,
+            "map_at_5": 0.924,
+            "map_at_10": 0.92612,
+            "map_at_20": 0.92696,
+            "map_at_50": 0.92712,
+            "map_at_100": 0.92719,
+            "recall_at_1": 0.896,
+            "recall_at_3": 0.95,
+            "recall_at_5": 0.964,
+            "recall_at_10": 0.978,
+            "recall_at_20": 0.99,
+            "recall_at_50": 0.994,
+            "recall_at_100": 0.998,
+            "precision_at_1": 0.896,
+            "precision_at_3": 0.31667,
+            "precision_at_5": 0.1928,
+            "precision_at_10": 0.0978,
+            "precision_at_20": 0.0495,
+            "precision_at_50": 0.01988,
+            "precision_at_100": 0.00998,
+            "mrr_at_1": 0.896,
+            "mrr_at_3": 0.9213333333333332,
+            "mrr_at_5": 0.9240333333333333,
+            "mrr_at_10": 0.9264857142857141,
+            "mrr_at_20": 0.9274158230658229,
+            "mrr_at_50": 0.9274847885830643,
+            "mrr_at_100": 0.9275602871585629,
+            "naucs_at_1_max": 0.8456651988738907,
+            "naucs_at_1_std": -0.12317729011766297,
+            "naucs_at_1_diff1": 0.9409423951490659,
+            "naucs_at_3_max": 0.8706816059757188,
+            "naucs_at_3_std": 0.006965452847808854,
+            "naucs_at_3_diff1": 0.9522875816993475,
+            "naucs_at_5_max": 0.9080558149185568,
+            "naucs_at_5_std": -0.04549227098247105,
+            "naucs_at_5_diff1": 0.9555192447349298,
+            "naucs_at_10_max": 0.8866819455054739,
+            "naucs_at_10_std": -0.08407605466429298,
+            "naucs_at_10_diff1": 0.9762329174093952,
+            "naucs_at_20_max": 0.9477124183006524,
+            "naucs_at_20_std": 0.25144724556488873,
+            "naucs_at_20_diff1": 1.0,
+            "naucs_at_50_max": 0.9564270152505304,
+            "naucs_at_50_std": 0.4352629940865033,
+            "naucs_at_50_diff1": 1.0,
+            "naucs_at_100_max": 1.0,
+            "naucs_at_100_std": 1.0,
+            "naucs_at_100_diff1": 1.0
+        },
+        "vidore/docvqa_test_subsampled": {
+            "ndcg_at_1": 0.54324,
+            "ndcg_at_3": 0.60994,
+            "ndcg_at_5": 0.6398,
+            "ndcg_at_10": 0.66199,
+            "ndcg_at_20": 0.67267,
+            "ndcg_at_50": 0.68225,
+            "ndcg_at_100": 0.68945,
+            "map_at_1": 0.54324,
+            "map_at_3": 0.59387,
+            "map_at_5": 0.61027,
+            "map_at_10": 0.61899,
+            "map_at_20": 0.62193,
+            "map_at_50": 0.62343,
+            "map_at_100": 0.62407,
+            "recall_at_1": 0.54324,
+            "recall_at_3": 0.65632,
+            "recall_at_5": 0.72949,
+            "recall_at_10": 0.80044,
+            "recall_at_20": 0.84257,
+            "recall_at_50": 0.89135,
+            "recall_at_100": 0.9357,
+            "precision_at_1": 0.54324,
+            "precision_at_3": 0.21877,
+            "precision_at_5": 0.1459,
+            "precision_at_10": 0.08004,
+            "precision_at_20": 0.04213,
+            "precision_at_50": 0.01783,
+            "precision_at_100": 0.00936,
+            "mrr_at_1": 0.5432372505543237,
+            "mrr_at_3": 0.5946045824094608,
+            "mrr_at_5": 0.6103473762010347,
+            "mrr_at_10": 0.6190493788054763,
+            "mrr_at_20": 0.6220782499013536,
+            "mrr_at_50": 0.623690385474884,
+            "mrr_at_100": 0.624317545713404,
+            "naucs_at_1_max": 0.5195120835206619,
+            "naucs_at_1_std": -0.31481029514111575,
+            "naucs_at_1_diff1": 0.8886195631998732,
+            "naucs_at_3_max": 0.4894265436758743,
+            "naucs_at_3_std": -0.35348286092835673,
+            "naucs_at_3_diff1": 0.825360351363726,
+            "naucs_at_5_max": 0.49365870598559275,
+            "naucs_at_5_std": -0.3667256163548182,
+            "naucs_at_5_diff1": 0.8190874936930554,
+            "naucs_at_10_max": 0.49415281281253026,
+            "naucs_at_10_std": -0.1787227124233066,
+            "naucs_at_10_diff1": 0.760124698410118,
+            "naucs_at_20_max": 0.4624420442016527,
+            "naucs_at_20_std": -0.14955421166412503,
+            "naucs_at_20_diff1": 0.7582711922759812,
+            "naucs_at_50_max": 0.46372165402671495,
+            "naucs_at_50_std": -0.009043079292315782,
+            "naucs_at_50_diff1": 0.7459081960812681,
+            "naucs_at_100_max": 0.41099442703800165,
+            "naucs_at_100_std": 0.4785954026968201,
+            "naucs_at_100_diff1": 0.7044383203056372
+        },
+        "vidore/infovqa_test_subsampled": {
+            "ndcg_at_1": 0.89676,
+            "ndcg_at_3": 0.92534,
+            "ndcg_at_5": 0.93031,
+            "ndcg_at_10": 0.935,
+            "ndcg_at_20": 0.93663,
+            "ndcg_at_50": 0.93904,
+            "ndcg_at_100": 0.94001,
+            "map_at_1": 0.89676,
+            "map_at_3": 0.91903,
+            "map_at_5": 0.92176,
+            "map_at_10": 0.92376,
+            "map_at_20": 0.92426,
+            "map_at_50": 0.92465,
+            "map_at_100": 0.92473,
+            "recall_at_1": 0.89676,
+            "recall_at_3": 0.94332,
+            "recall_at_5": 0.95547,
+            "recall_at_10": 0.96964,
+            "recall_at_20": 0.97571,
+            "recall_at_50": 0.98785,
+            "recall_at_100": 0.99393,
+            "precision_at_1": 0.89676,
+            "precision_at_3": 0.31444,
+            "precision_at_5": 0.19109,
+            "precision_at_10": 0.09696,
+            "precision_at_20": 0.04879,
+            "precision_at_50": 0.01976,
+            "precision_at_100": 0.00994,
+            "mrr_at_1": 0.8967611336032388,
+            "mrr_at_3": 0.9183535762483129,
+            "mrr_at_5": 0.9206815114709849,
+            "mrr_at_10": 0.9232191054559475,
+            "mrr_at_20": 0.9235380847222951,
+            "mrr_at_50": 0.9239302146072342,
+            "mrr_at_100": 0.9240125185515768,
+            "naucs_at_1_max": 0.7062394427119798,
+            "naucs_at_1_std": -0.2812879238976883,
+            "naucs_at_1_diff1": 0.9410064894465787,
+            "naucs_at_3_max": 0.7564908149226892,
+            "naucs_at_3_std": -0.3059756682732854,
+            "naucs_at_3_diff1": 0.9422566807977654,
+            "naucs_at_5_max": 0.84758972902799,
+            "naucs_at_5_std": -0.0929285302133143,
+            "naucs_at_5_diff1": 0.9450692388254637,
+            "naucs_at_10_max": 0.8860131032188592,
+            "naucs_at_10_std": 0.24420167069765694,
+            "naucs_at_10_diff1": 0.9368484108193146,
+            "naucs_at_20_max": 0.8806609405034168,
+            "naucs_at_20_std": 0.28312028971462133,
+            "naucs_at_20_diff1": 0.9428274225349419,
+            "naucs_at_50_max": 0.78308879001761,
+            "naucs_at_50_std": 0.08727770914673263,
+            "naucs_at_50_diff1": 0.9537108770403242,
+            "naucs_at_100_max": 0.6097113980568468,
+            "naucs_at_100_std": -0.06311386037266957,
+            "naucs_at_100_diff1": 0.9074217540806789
+        },
+        "vidore/tabfquad_test_subsampled": {
+            "ndcg_at_1": 0.90714,
+            "ndcg_at_3": 0.94809,
+            "ndcg_at_5": 0.95085,
+            "ndcg_at_10": 0.95556,
+            "ndcg_at_20": 0.95556,
+            "ndcg_at_50": 0.95633,
+            "ndcg_at_100": 0.95633,
+            "map_at_1": 0.90714,
+            "map_at_3": 0.93869,
+            "map_at_5": 0.94012,
+            "map_at_10": 0.94212,
+            "map_at_20": 0.94212,
+            "map_at_50": 0.94227,
+            "map_at_100": 0.94227,
+            "recall_at_1": 0.90714,
+            "recall_at_3": 0.975,
+            "recall_at_5": 0.98214,
+            "recall_at_10": 0.99643,
+            "recall_at_20": 0.99643,
+            "recall_at_50": 1.0,
+            "recall_at_100": 1.0,
+            "precision_at_1": 0.90714,
+            "precision_at_3": 0.325,
+            "precision_at_5": 0.19643,
+            "precision_at_10": 0.09964,
+            "precision_at_20": 0.04982,
+            "precision_at_50": 0.02,
+            "precision_at_100": 0.01,
+            "mrr_at_1": 0.9071428571428571,
+            "mrr_at_3": 0.9386904761904761,
+            "mrr_at_5": 0.9401190476190476,
+            "mrr_at_10": 0.9421173469387754,
+            "mrr_at_20": 0.9421173469387754,
+            "mrr_at_50": 0.9422602040816326,
+            "mrr_at_100": 0.9422602040816326,
+            "naucs_at_1_max": 0.47509516627163817,
+            "naucs_at_1_std": 0.09654887596064192,
+            "naucs_at_1_diff1": 0.9256625727213957,
+            "naucs_at_3_max": 0.7953181272509063,
+            "naucs_at_3_std": 0.6569294384420459,
+            "naucs_at_3_diff1": 0.9626517273576122,
+            "naucs_at_5_max": 0.9477124183006519,
+            "naucs_at_5_std": 0.8585434173669502,
+            "naucs_at_5_diff1": 0.9477124183006519,
+            "naucs_at_10_max": 1.0,
+            "naucs_at_10_std": 1.0,
+            "naucs_at_10_diff1": 0.8692810457516478,
+            "naucs_at_20_max": 1.0,
+            "naucs_at_20_std": 1.0,
+            "naucs_at_20_diff1": 0.8692810457516478,
+            "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
+        },
+        "vidore/tatdqa_test": {
+            "ndcg_at_1": 0.68165,
+            "ndcg_at_3": 0.78589,
+            "ndcg_at_5": 0.80738,
+            "ndcg_at_10": 0.81887,
+            "ndcg_at_20": 0.82338,
+            "ndcg_at_50": 0.82868,
+            "ndcg_at_100": 0.82966,
+            "map_at_1": 0.68165,
+            "map_at_3": 0.76094,
+            "map_at_5": 0.77284,
+            "map_at_10": 0.77775,
+            "map_at_20": 0.77902,
+            "map_at_50": 0.77992,
+            "map_at_100": 0.78,
+            "recall_at_1": 0.68165,
+            "recall_at_3": 0.85784,
+            "recall_at_5": 0.91009,
+            "recall_at_10": 0.94471,
+            "recall_at_20": 0.96233,
+            "recall_at_50": 0.98846,
+            "recall_at_100": 0.99453,
+            "precision_at_1": 0.68165,
+            "precision_at_3": 0.28595,
+            "precision_at_5": 0.18202,
+            "precision_at_10": 0.09447,
+            "precision_at_20": 0.04812,
+            "precision_at_50": 0.01977,
+            "precision_at_100": 0.00995,
+            "mrr_at_1": 0.6822600243013366,
+            "mrr_at_3": 0.7609356014580796,
+            "mrr_at_5": 0.7725394896719318,
+            "mrr_at_10": 0.7775212636695014,
+            "mrr_at_20": 0.7787535437042965,
+            "mrr_at_50": 0.7796543784238207,
+            "mrr_at_100": 0.7797401545799822,
+            "naucs_at_1_max": 0.16062026715795888,
+            "naucs_at_1_std": -0.3264360293606425,
+            "naucs_at_1_diff1": 0.8234210928574244,
+            "naucs_at_3_max": 0.2735402374223285,
+            "naucs_at_3_std": -0.2518265754222236,
+            "naucs_at_3_diff1": 0.7126512468213168,
+            "naucs_at_5_max": 0.3207976518601587,
+            "naucs_at_5_std": -0.09980902320534159,
+            "naucs_at_5_diff1": 0.654620096904173,
+            "naucs_at_10_max": 0.4248907897527349,
+            "naucs_at_10_std": 0.05751189029665147,
+            "naucs_at_10_diff1": 0.6072701680557849,
+            "naucs_at_20_max": 0.5189102534669143,
+            "naucs_at_20_std": 0.17852289719761627,
+            "naucs_at_20_diff1": 0.5826792796971454,
+            "naucs_at_50_max": 0.6766878761446519,
+            "naucs_at_50_std": 0.4444418209829138,
+            "naucs_at_50_diff1": 0.5707904926948768,
+            "naucs_at_100_max": 0.5171029913955458,
+            "naucs_at_100_std": 0.4414823767216705,
+            "naucs_at_100_diff1": 0.48651595702377487
+        },
+        "vidore/shiftproject_test": {
+            "ndcg_at_1": 0.79,
+            "ndcg_at_3": 0.88309,
+            "ndcg_at_5": 0.88309,
+            "ndcg_at_10": 0.88666,
+            "ndcg_at_20": 0.89172,
+            "ndcg_at_50": 0.89372,
+            "ndcg_at_100": 0.89546,
+            "map_at_1": 0.79,
+            "map_at_3": 0.86,
+            "map_at_5": 0.86,
+            "map_at_10": 0.86167,
+            "map_at_20": 0.86308,
+            "map_at_50": 0.8634,
+            "map_at_100": 0.86359,
+            "recall_at_1": 0.79,
+            "recall_at_3": 0.95,
+            "recall_at_5": 0.95,
+            "recall_at_10": 0.96,
+            "recall_at_20": 0.98,
+            "recall_at_50": 0.99,
+            "recall_at_100": 1.0,
+            "precision_at_1": 0.79,
+            "precision_at_3": 0.31667,
+            "precision_at_5": 0.19,
+            "precision_at_10": 0.096,
+            "precision_at_20": 0.049,
+            "precision_at_50": 0.0198,
+            "precision_at_100": 0.01,
+            "mrr_at_1": 0.79,
+            "mrr_at_3": 0.8633333333333333,
+            "mrr_at_5": 0.8633333333333333,
+            "mrr_at_10": 0.865,
+            "mrr_at_20": 0.8664354066985647,
+            "mrr_at_50": 0.8667579873437259,
+            "mrr_at_100": 0.8669466665890089,
+            "naucs_at_1_max": 0.039218986702575266,
+            "naucs_at_1_std": -0.30031019308918766,
+            "naucs_at_1_diff1": 0.8456248346839152,
+            "naucs_at_3_max": 0.5220354808590087,
+            "naucs_at_3_std": -0.057609710550887504,
+            "naucs_at_3_diff1": 0.8160597572362241,
+            "naucs_at_5_max": 0.5220354808590145,
+            "naucs_at_5_std": -0.05760971055088009,
+            "naucs_at_5_diff1": 0.8160597572362281,
+            "naucs_at_10_max": 0.4352240896358576,
+            "naucs_at_10_std": -0.10270774976656832,
+            "naucs_at_10_diff1": 0.9305555555555542,
+            "naucs_at_20_max": 0.1914098972922579,
+            "naucs_at_20_std": -0.3968253968253954,
+            "naucs_at_20_diff1": 0.861111111111116,
+            "naucs_at_50_max": 0.554154995331464,
+            "naucs_at_50_std": 0.35807656395892007,
+            "naucs_at_50_diff1": 1.0,
+            "naucs_at_100_max": null,
+            "naucs_at_100_std": null,
+            "naucs_at_100_diff1": null
+        },
+        "vidore/syntheticDocQA_artificial_intelligence_test": {
+            "ndcg_at_1": 1.0,
+            "ndcg_at_3": 1.0,
+            "ndcg_at_5": 1.0,
+            "ndcg_at_10": 1.0,
+            "ndcg_at_20": 1.0,
+            "ndcg_at_50": 1.0,
+            "ndcg_at_100": 1.0,
+            "map_at_1": 1.0,
+            "map_at_3": 1.0,
+            "map_at_5": 1.0,
+            "map_at_10": 1.0,
+            "map_at_20": 1.0,
+            "map_at_50": 1.0,
+            "map_at_100": 1.0,
+            "recall_at_1": 1.0,
+            "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": 1.0,
+            "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": 1.0,
+            "mrr_at_3": 1.0,
+            "mrr_at_5": 1.0,
+            "mrr_at_10": 1.0,
+            "mrr_at_20": 1.0,
+            "mrr_at_50": 1.0,
+            "mrr_at_100": 1.0,
+            "naucs_at_1_max": null,
+            "naucs_at_1_std": null,
+            "naucs_at_1_diff1": null,
+            "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
+        },
+        "vidore/syntheticDocQA_energy_test": {
+            "ndcg_at_1": 0.94,
+            "ndcg_at_3": 0.95893,
+            "ndcg_at_5": 0.95893,
+            "ndcg_at_10": 0.96208,
+            "ndcg_at_20": 0.96718,
+            "ndcg_at_50": 0.96718,
+            "ndcg_at_100": 0.96718,
+            "map_at_1": 0.94,
+            "map_at_3": 0.955,
+            "map_at_5": 0.955,
+            "map_at_10": 0.95625,
+            "map_at_20": 0.95767,
+            "map_at_50": 0.95767,
+            "map_at_100": 0.95767,
+            "recall_at_1": 0.94,
+            "recall_at_3": 0.97,
+            "recall_at_5": 0.97,
+            "recall_at_10": 0.98,
+            "recall_at_20": 1.0,
+            "recall_at_50": 1.0,
+            "recall_at_100": 1.0,
+            "precision_at_1": 0.94,
+            "precision_at_3": 0.32333,
+            "precision_at_5": 0.194,
+            "precision_at_10": 0.098,
+            "precision_at_20": 0.05,
+            "precision_at_50": 0.02,
+            "precision_at_100": 0.01,
+            "mrr_at_1": 0.94,
+            "mrr_at_3": 0.955,
+            "mrr_at_5": 0.955,
+            "mrr_at_10": 0.9566666666666667,
+            "mrr_at_20": 0.9582142857142857,
+            "mrr_at_50": 0.9582142857142857,
+            "mrr_at_100": 0.9582142857142857,
+            "naucs_at_1_max": 0.49004046062869583,
+            "naucs_at_1_std": -0.6582633053221264,
+            "naucs_at_1_diff1": 1.0,
+            "naucs_at_3_max": 0.7424525365701778,
+            "naucs_at_3_std": -1.040616246498596,
+            "naucs_at_3_diff1": 1.0,
+            "naucs_at_5_max": 0.742452536570183,
+            "naucs_at_5_std": -1.040616246498598,
+            "naucs_at_5_diff1": 1.0,
+            "naucs_at_10_max": 0.9346405228758136,
+            "naucs_at_10_std": -0.690943043884218,
+            "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
+        },
+        "vidore/syntheticDocQA_government_reports_test": {
+            "ndcg_at_1": 0.92,
+            "ndcg_at_3": 0.95655,
+            "ndcg_at_5": 0.96085,
+            "ndcg_at_10": 0.96419,
+            "ndcg_at_20": 0.96419,
+            "ndcg_at_50": 0.96419,
+            "ndcg_at_100": 0.96419,
+            "map_at_1": 0.92,
+            "map_at_3": 0.94833,
+            "map_at_5": 0.95083,
+            "map_at_10": 0.95226,
+            "map_at_20": 0.95226,
+            "map_at_50": 0.95226,
+            "map_at_100": 0.95226,
+            "recall_at_1": 0.92,
+            "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": 0.92,
+            "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": 0.9574999999999999,
+            "mrr_at_20": 0.9574999999999999,
+            "mrr_at_50": 0.9574999999999999,
+            "mrr_at_100": 0.9574999999999999,
+            "naucs_at_1_max": 0.6289682539682547,
+            "naucs_at_1_std": 0.44461951447245585,
+            "naucs_at_1_diff1": 0.9509803921568633,
+            "naucs_at_3_max": 1.0,
+            "naucs_at_3_std": 0.3384687208216551,
+            "naucs_at_3_diff1": 0.9346405228758099,
+            "naucs_at_5_max": 1.0,
+            "naucs_at_5_std": 0.5541549953314738,
+            "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_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
+        },
+        "vidore/syntheticDocQA_healthcare_industry_test": {
+            "ndcg_at_1": 0.94,
+            "ndcg_at_3": 0.97655,
+            "ndcg_at_5": 0.97655,
+            "ndcg_at_10": 0.97655,
+            "ndcg_at_20": 0.97655,
+            "ndcg_at_50": 0.97655,
+            "ndcg_at_100": 0.97655,
+            "map_at_1": 0.94,
+            "map_at_3": 0.96833,
+            "map_at_5": 0.96833,
+            "map_at_10": 0.96833,
+            "map_at_20": 0.96833,
+            "map_at_50": 0.96833,
+            "map_at_100": 0.96833,
+            "recall_at_1": 0.94,
+            "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": 0.94,
+            "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": 0.95,
+            "mrr_at_3": 0.9733333333333333,
+            "mrr_at_5": 0.9733333333333333,
+            "mrr_at_10": 0.9733333333333333,
+            "mrr_at_20": 0.9733333333333333,
+            "mrr_at_50": 0.9733333333333333,
+            "mrr_at_100": 0.9733333333333333,
+            "naucs_at_1_max": 0.5662931839402436,
+            "naucs_at_1_std": 0.18837535014005719,
+            "naucs_at_1_diff1": 0.9782135076252712,
+            "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_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553a9ca2ae242a0290de05f7b69345a1ac6c9250cf01a2b678642efee4ed5df4
+size 5496