Visual Document Retrieval
PEFT
Safetensors
ColPali
vidore
multimodal_embedding
multilingual_embedding
Text-to-Visual Document (T→VD) retrieval
brian-remodl commited on
Commit
ee9bfd9
·
verified ·
1 Parent(s): 0ffad74

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
LICENSE ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Qwen RESEARCH LICENSE AGREEMENT
2
+
3
+ Qwen RESEARCH LICENSE AGREEMENT Release Date: September 19, 2024
4
+
5
+ By clicking to agree or by using or distributing any portion or element of the Qwen Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
6
+
7
+ 1. Definitions
8
+ a. This Qwen RESEARCH LICENSE AGREEMENT (this "Agreement") shall mean the terms and conditions for use, reproduction, distribution and modification of the Materials as defined by this Agreement.
9
+ b. "We" (or "Us") shall mean Alibaba Cloud.
10
+ c. "You" (or "Your") shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Materials for any purpose and in any field of use.
11
+ d. "Third Parties" shall mean individuals or legal entities that are not under common control with us or you.
12
+ e. "Qwen" shall mean the large language models, and software and algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by us.
13
+ f. "Materials" shall mean, collectively, Alibaba Cloud's proprietary Qwen and Documentation (and any portion thereof) made available under this Agreement.
14
+ g. "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files.
15
+ h. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
16
+ i. "Non-Commercial" shall mean for research or evaluation purposes only.
17
+
18
+ 2. Grant of Rights
19
+ a. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Alibaba Cloud's intellectual property or other rights owned by us embodied in the Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Materials FOR NON-COMMERCIAL PURPOSES ONLY.
20
+ b. If you are commercially using the Materials, you shall request a license from us.
21
+
22
+ 3. Redistribution
23
+ You may distribute copies or make the Materials, or derivative works thereof, available as part of a product or service that contains any of them, with or without modifications, and in Source or Object form, provided that you meet the following conditions:
24
+ a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement;
25
+ b. You shall cause any modified files to carry prominent notices stating that you changed the files;
26
+ c. You shall retain in all copies of the Materials that you distribute the following attribution notices within a "Notice" text file distributed as a part of such copies: "Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved."; and
27
+ d. You may add your own copyright statement to your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of your modifications, or for any such derivative works as a whole, provided your use, reproduction, and distribution of the work otherwise complies with the terms and conditions of this Agreement.
28
+
29
+ 4. Rules of use
30
+ a. The Materials may be subject to export controls or restrictions in China, the United States or other countries or regions. You shall comply with applicable laws and regulations in your use of the Materials.
31
+ b. If you use the Materials or any outputs or results therefrom to create, train, fine-tune, or improve an AI model that is distributed or made available, you shall prominently display “Built with Qwen” or “Improved using Qwen” in the related product documentation.
32
+
33
+ 5. Intellectual Property
34
+ a. We retain ownership of all intellectual property rights in and to the Materials and derivatives made by or for us. Conditioned upon compliance with the terms and conditions of this Agreement, with respect to any derivative works and modifications of the Materials that are made by you, you are and will be the owner of such derivative works and modifications.
35
+ b. No trademark license is granted to use the trade names, trademarks, service marks, or product names of us, except as required to fulfill notice requirements under this Agreement or as required for reasonable and customary use in describing and redistributing the Materials.
36
+ c. If you commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against us or any entity alleging that the Materials or any output therefrom, or any part of the foregoing, infringe any intellectual property or other right owned or licensable by you, then all licenses granted to you under this Agreement shall terminate as of the date such lawsuit or other proceeding is commenced or brought.
37
+ 6. Disclaimer of Warranty and Limitation of Liability
38
+ a. We are not obligated to support, update, provide training for, or develop any further version of the Qwen Materials or to grant any license thereto.
39
+ b. THE MATERIALS ARE PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. WE MAKE NO WARRANTY AND ASSUME NO RESPONSIBILITY FOR THE SAFETY OR STABILITY OF THE MATERIALS AND ANY OUTPUT THEREFROM.
40
+ c. IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MATERIALS OR ANY OUTPUT OF IT, NO MATTER HOW IT’S CAUSED.
41
+ d. You will defend, indemnify and hold harmless us from and against any claim by any third party arising out of or related to your use or distribution of the Materials.
42
+
43
+ 7. Survival and Termination.
44
+ a. The term of this Agreement shall commence upon your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein.
45
+ b. We may terminate this Agreement if you breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, you must delete and cease use of the Materials. Sections 6 and 8 shall survive the termination of this Agreement.
46
+
47
+ 8. Governing Law and Jurisdiction.
48
+ a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of China, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
49
+ b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement.
50
+ 9. Other Terms and Conditions.
51
+ a. Any arrangements, understandings, or agreements regarding the Material not stated herein are separate from and independent of the terms and conditions of this Agreement. You shall request a separate license from us, if you use the Materials in ways not expressly agreed to in this Agreement.
52
+ b. We shall not be bound by any additional or different terms or conditions communicated by you unless expressly agreed.
README.md ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-VL-3B-Instruct
3
+ library_name: peft
4
+ datasets:
5
+ - llamaindex/vdr-multilingual-train
6
+ - nomic-ai/colpali_train_set_split_by_source
7
+ language:
8
+ - en
9
+ - it
10
+ - fr
11
+ - de
12
+ - es
13
+ pipeline_tag: visual-document-retrieval
14
+ tags:
15
+ - vidore
16
+ - colpali
17
+ - multimodal_embedding
18
+ - multilingual_embedding
19
+ - Text-to-Visual Document (T→VD) retrieval
20
+ ---
21
+
22
+ # ColNomic Embed Multimodal 3B: State-of-the-Art Visual Document Retrieval
23
+
24
+ `colnomic-embed-multimodal-3b` is a multi-vector state-of-the-art multimodal embedding model that excels at visual document retrieval tasks:
25
+
26
+ - **High Performance**: Achieves 61.2 NDCG@5 on Vidore-v2, outperforming all other models except ColNomic Embed Multimodal 7B
27
+ - **Unified Text-Image Encoding**: Directly encodes interleaved text and images without complex preprocessing
28
+ - **Advanced Architecture**: 3B parameter multimodal embedding model
29
+ - **Open-Weights**: Model weights available for research use
30
+
31
+ ## Performance
32
+
33
+ | Model | Avg. | ESG Restaurant Human | Econ Macro Multi. | AXA Multi. | MIT Bio | ESG Restaurant Synth. | ESG Restaurant Synth. Multi. | MIT Bio Multi. | AXA | Econ. Macro |
34
+ |-------|------|----------------------|-------------------|------------|---------|----------------------|----------------------------|---------------|-----|------------|
35
+ | [ColNomic Embed Multimodal 7B](https://huggingface.co/nomic-ai/colnomic-embed-multimodal-7b)| 62.7 | 73.9 | 54.7 | 61.3 | 66.1 | 57.3 | 56.7 | 64.2 | 68.3 | 61.6 |
36
+ | **ColNomic Embed Multimodal** 3B | 61.2 | 65.8 | 55.4 | 61.0 | 63.5 | 56.6 | 57.2 | 62.5 | 68.8 | 60.2 |
37
+ | T-Systems ColQwen2.5-3B | 59.9 | 72.1 | 51.2 | 60.0 | 65.3 | 51.7 | 53.3 | 61.7 | 69.3 | 54.8 |
38
+ | [Nomic Embed Multimodal 7B](https://huggingface.co/nomic-ai/nomic-embed-multimodal-7b) | 59.7 | 65.7 | 57.7 | 59.3 | 64.0 | 49.2 | 51.9 | 61.2 | 66.3 | 63.1 |
39
+ | GME Qwen2 7B | 59.0 | 65.8 | 56.2 | 55.4 | 64.0 | 54.3 | 56.7 | 55.1 | 60.7 | 62.9 |
40
+ | [Nomic Embed Multimodal 3B](https://huggingface.co/nomic-ai/nomic-embed-multimodal-3b) | 58.8 | 59.8 | 57.5 | 58.8 | 62.5 | 49.4 | 49.4 | 58.6 | 69.6 | 63.5 |
41
+ | Llama Index vdr-2b-multi-v1 | 58.4 | 63.1 | 52.8 | 61.0 | 60.6 | 50.3 | 51.2 | 56.9 | 68.8 | 61.2 |
42
+ | Voyage Multimodal 3 | 55.0 | 56.1 | 55.0 | 59.5 | 56.4 | 47.2 | 46.2 | 51.5 | 64.1 | 58.8 |
43
+
44
+ ## Getting Started
45
+
46
+ To use `colnomic-embed-multimodal-3b`, please install `colpali` from source
47
+
48
+ ```bash
49
+ pip install git+https://github.com/illuin-tech/colpali.git
50
+ ```
51
+
52
+
53
+ ```python
54
+ import torch
55
+ from PIL import Image
56
+ from transformers.utils.import_utils import is_flash_attn_2_available
57
+
58
+ from colpali_engine.models import ColQwen2_5, ColQwen2_5_Processor
59
+
60
+ model_name = "nomic-ai/colnomic-embed-multimodal-3b"
61
+
62
+ model = ColQwen2_5.from_pretrained(
63
+ model_name,
64
+ torch_dtype=torch.bfloat16,
65
+ device_map="cuda:0", # or "mps" if on Apple Silicon
66
+ attn_implementation="flash_attention_2" if is_flash_attn_2_available() else None,
67
+ ).eval()
68
+
69
+ processor = ColQwen2_5_Processor.from_pretrained(model_name)
70
+
71
+ # Your inputs
72
+ images = [
73
+ Image.new("RGB", (128, 128), color="white"),
74
+ Image.new("RGB", (64, 32), color="black"),
75
+ ]
76
+ queries = [
77
+ "What is the organizational structure for our R&D department?",
78
+ "Can you provide a breakdown of last year’s financial performance?",
79
+ ]
80
+
81
+ # Process the inputs
82
+ batch_images = processor.process_images(images).to(model.device)
83
+ batch_queries = processor.process_queries(queries).to(model.device)
84
+
85
+ # Forward pass
86
+ with torch.no_grad():
87
+ image_embeddings = model(**batch_images)
88
+ query_embeddings = model(**batch_queries)
89
+
90
+ scores = processor.score_multi_vector(query_embeddings, image_embeddings)
91
+ ```
92
+
93
+
94
+ ## Model Architecture
95
+
96
+ - **Total Parameters**: 3B
97
+ - **Training Approach**: Fine-tuned from Qwen2.5-VL 3B Instruct
98
+ - **Architecture Type**: Vision-Language Model with unified text and image input processing
99
+ - **Key Innovations**:
100
+ - Same-source sampling to create harder in-batch negatives
101
+ - Multi-vector output option for enhanced performance
102
+
103
+ ## Integration with RAG Workflows
104
+
105
+ Nomic Embed Multimodal 3B seamlessly integrates with Retrieval Augmented Generation (RAG) workflows:
106
+
107
+ 1. **Direct Document Embedding**: Skip OCR and complex processing by directly embedding document page images
108
+ 2. **Faster Processing**: Eliminate preprocessing steps for quicker indexing
109
+ 3. **More Complete Information**: Capture both textual and visual cues in a single embedding
110
+ 4. **Simple Implementation**: Use the same API for both text and images
111
+
112
+ ## Recommended Use Cases
113
+
114
+ The model excels at handling real-world document retrieval scenarios that challenge traditional text-only systems:
115
+
116
+ - **Research Papers**: Capture equations, diagrams, and tables
117
+ - **Technical Documentation**: Encode code blocks, flowcharts, and screenshots
118
+ - **Product Catalogs**: Represent images, specifications, and pricing tables
119
+ - **Financial Reports**: Embed charts, graphs, and numerical data
120
+ - **Visually Rich Content**: Where layout and visual information are important
121
+ - **Multilingual Documents**: Where visual context provides important cues
122
+
123
+ ## Training Details
124
+
125
+ ColNomic Embed Multimodal 3B was developed through several key innovations:
126
+
127
+ 1. **Sampling From the Same Source**: Forcing sampling from the same dataset source creates harder in-batch negatives, preventing the model from learning dataset artifacts.
128
+
129
+ 2. **Multi-Vector Configuration**: Providing a multi-vector variant that achieves higher performance than the dense variant.
130
+
131
+ ## Limitations
132
+
133
+ - Performance may vary when processing documents with unconventional layouts or unusual visual elements
134
+ - While it handles multiple languages, performance is strongest on English content
135
+ - Processing very large or complex documents may require dividing them into smaller chunks
136
+ - Performance on documents with handwriting or heavily stylized fonts may be reduced
137
+
138
+ ## Join the Nomic Community
139
+
140
+ - Nomic Embed Ecosystem: [https://www.nomic.ai/embed](https://www.nomic.ai/embed)
141
+ - Website: [https://nomic.ai](https://nomic.ai)
142
+ - Twitter: [https://twitter.com/nomic_ai](https://twitter.com/nomic_ai)
143
+ - Discord: [https://discord.gg/myY5YDR8z8](https://discord.gg/myY5YDR8z8)
144
+
145
+ ## Citation
146
+
147
+ If you find this model useful in your research or applications, please consider citing:
148
+
149
+ ```bibtex
150
+ @misc{faysse2024colpaliefficientdocumentretrieval,
151
+ title={ColPali: Efficient Document Retrieval with Vision Language Models},
152
+ author={Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and Céline Hudelot and Pierre Colombo},
153
+ year={2024},
154
+ eprint={2407.01449},
155
+ archivePrefix={arXiv},
156
+ primaryClass={cs.IR},
157
+ url={https://arxiv.org/abs/2407.01449},
158
+ }
159
+ @misc{ma2024unifyingmultimodalretrievaldocument,
160
+ title={Unifying Multimodal Retrieval via Document Screenshot Embedding},
161
+ author={Xueguang Ma and Sheng-Chieh Lin and Minghan Li and Wenhu Chen and Jimmy Lin},
162
+ year={2024},
163
+ eprint={2406.11251},
164
+ archivePrefix={arXiv},
165
+ primaryClass={cs.IR},
166
+ url={https://arxiv.org/abs/2406.11251},
167
+ }
168
+ @misc{nomicembedmultimodal2025,
169
+ title={Nomic Embed Multimodal: Interleaved Text, Image, and Screenshots for Visual Document Retrieval},
170
+ author={Nomic Team},
171
+ year={2025},
172
+ publisher={Nomic AI},
173
+ url={https://nomic.ai/blog/posts/nomic-embed-multimodal},
174
+ }
175
+ ```
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "vidore/colqwen2.5-base",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": "gaussian",
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 32,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
26
+ "task_type": "FEATURE_EXTRACTION",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af23b67a003f94075927e2ed853edc7498dd4e9353f9c75f88e45859811afdc3
3
+ size 239815040
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "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 %}"
3
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.49.0"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 1003520,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "ColQwen2_5_Processor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 1003520,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_num_visual_tokens": 1280,
3
+ "processor_class": "ColQwen2_5_Processor"
4
+ }
results.json ADDED
@@ -0,0 +1,1104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vidore/arxivqa_test_subsampled":{
3
+ "ndcg_at_1":0.824,
4
+ "ndcg_at_3":0.86202,
5
+ "ndcg_at_5":0.87442,
6
+ "ndcg_at_10":0.88303,
7
+ "ndcg_at_20":0.88861,
8
+ "ndcg_at_50":0.8927,
9
+ "ndcg_at_100":0.89339,
10
+ "map_at_1":0.824,
11
+ "map_at_3":0.853,
12
+ "map_at_5":0.8599,
13
+ "map_at_10":0.86358,
14
+ "map_at_20":0.86512,
15
+ "map_at_50":0.86583,
16
+ "map_at_100":0.86591,
17
+ "recall_at_1":0.824,
18
+ "recall_at_3":0.888,
19
+ "recall_at_5":0.918,
20
+ "recall_at_10":0.944,
21
+ "recall_at_20":0.966,
22
+ "recall_at_50":0.986,
23
+ "recall_at_100":0.99,
24
+ "precision_at_1":0.824,
25
+ "precision_at_3":0.296,
26
+ "precision_at_5":0.1836,
27
+ "precision_at_10":0.0944,
28
+ "precision_at_20":0.0483,
29
+ "precision_at_50":0.01972,
30
+ "precision_at_100":0.0099,
31
+ "mrr_at_1":0.832,
32
+ "mrr_at_3":0.856,
33
+ "mrr_at_5":0.8632,
34
+ "mrr_at_10":0.86755,
35
+ "mrr_at_20":0.8687646325896324,
36
+ "mrr_at_50":0.8694855987079559,
37
+ "mrr_at_100":0.8695150104726618,
38
+ "naucs_at_1_max":0.8110100305865411,
39
+ "naucs_at_1_std":0.07361011155091818,
40
+ "naucs_at_1_diff1":0.9603893037063689,
41
+ "naucs_at_3_max":0.7977881493506478,
42
+ "naucs_at_3_std":0.013342126623376577,
43
+ "naucs_at_3_diff1":0.9239464962121198,
44
+ "naucs_at_5_max":0.8150463437407489,
45
+ "naucs_at_5_std":0.14904010384641533,
46
+ "naucs_at_5_diff1":0.9183006535947713,
47
+ "naucs_at_10_max":0.8759670534880637,
48
+ "naucs_at_10_std":0.2408463385354136,
49
+ "naucs_at_10_diff1":0.9323062558356668,
50
+ "naucs_at_20_max":0.9013016971494501,
51
+ "naucs_at_20_std":0.4259076179491429,
52
+ "naucs_at_20_diff1":0.9115724721261116,
53
+ "naucs_at_50_max":0.9229691876750605,
54
+ "naucs_at_50_std":0.7222889155662164,
55
+ "naucs_at_50_diff1":0.9019607843137241,
56
+ "naucs_at_100_max":0.8921568627450854,
57
+ "naucs_at_100_std":0.6373482726423866,
58
+ "naucs_at_100_diff1":0.9183006535947666
59
+ },
60
+ "vidore/docvqa_test_subsampled":{
61
+ "ndcg_at_1":0.52993,
62
+ "ndcg_at_3":0.59967,
63
+ "ndcg_at_5":0.61961,
64
+ "ndcg_at_10":0.63197,
65
+ "ndcg_at_20":0.64596,
66
+ "ndcg_at_50":0.65515,
67
+ "ndcg_at_100":0.66198,
68
+ "map_at_1":0.52993,
69
+ "map_at_3":0.58241,
70
+ "map_at_5":0.59339,
71
+ "map_at_10":0.59817,
72
+ "map_at_20":0.602,
73
+ "map_at_50":0.60345,
74
+ "map_at_100":0.60405,
75
+ "recall_at_1":0.52993,
76
+ "recall_at_3":0.64967,
77
+ "recall_at_5":0.69845,
78
+ "recall_at_10":0.73836,
79
+ "recall_at_20":0.79379,
80
+ "recall_at_50":0.84035,
81
+ "recall_at_100":0.88248,
82
+ "precision_at_1":0.52993,
83
+ "precision_at_3":0.21656,
84
+ "precision_at_5":0.13969,
85
+ "precision_at_10":0.07384,
86
+ "precision_at_20":0.03969,
87
+ "precision_at_50":0.01681,
88
+ "precision_at_100":0.00882,
89
+ "mrr_at_1":0.5277161862527716,
90
+ "mrr_at_3":0.5776053215077607,
91
+ "mrr_at_5":0.5888026607538803,
92
+ "mrr_at_10":0.5944919579065918,
93
+ "mrr_at_20":0.5983219637865657,
94
+ "mrr_at_50":0.5999309966010471,
95
+ "mrr_at_100":0.6005501639541099,
96
+ "naucs_at_1_max":0.37096765728763215,
97
+ "naucs_at_1_std":0.5363118108228696,
98
+ "naucs_at_1_diff1":0.9084586513989499,
99
+ "naucs_at_3_max":0.28536364371043943,
100
+ "naucs_at_3_std":0.656382780997437,
101
+ "naucs_at_3_diff1":0.8754285629546056,
102
+ "naucs_at_5_max":0.26490606879524303,
103
+ "naucs_at_5_std":0.6794242484186521,
104
+ "naucs_at_5_diff1":0.8670235151833391,
105
+ "naucs_at_10_max":0.17906145941266727,
106
+ "naucs_at_10_std":0.71951378124067,
107
+ "naucs_at_10_diff1":0.8623037540857623,
108
+ "naucs_at_20_max":0.039717430802327786,
109
+ "naucs_at_20_std":0.77907518789845,
110
+ "naucs_at_20_diff1":0.8711346514573685,
111
+ "naucs_at_50_max":-0.06591984153859125,
112
+ "naucs_at_50_std":0.8944335077781369,
113
+ "naucs_at_50_diff1":0.872338054901137,
114
+ "naucs_at_100_max":-0.18390488993971363,
115
+ "naucs_at_100_std":0.9432351742842897,
116
+ "naucs_at_100_diff1":0.8529357662557685
117
+ },
118
+ "vidore/infovqa_test_subsampled":{
119
+ "ndcg_at_1":0.89069,
120
+ "ndcg_at_3":0.9279,
121
+ "ndcg_at_5":0.93217,
122
+ "ndcg_at_10":0.93547,
123
+ "ndcg_at_20":0.9379,
124
+ "ndcg_at_50":0.93869,
125
+ "ndcg_at_100":0.93902,
126
+ "map_at_1":0.89069,
127
+ "map_at_3":0.91903,
128
+ "map_at_5":0.92146,
129
+ "map_at_10":0.92284,
130
+ "map_at_20":0.92344,
131
+ "map_at_50":0.92356,
132
+ "map_at_100":0.92359,
133
+ "recall_at_1":0.89069,
134
+ "recall_at_3":0.95344,
135
+ "recall_at_5":0.96356,
136
+ "recall_at_10":0.97368,
137
+ "recall_at_20":0.98381,
138
+ "recall_at_50":0.98785,
139
+ "recall_at_100":0.98988,
140
+ "precision_at_1":0.89069,
141
+ "precision_at_3":0.31781,
142
+ "precision_at_5":0.19271,
143
+ "precision_at_10":0.09737,
144
+ "precision_at_20":0.04919,
145
+ "precision_at_50":0.01976,
146
+ "precision_at_100":0.0099,
147
+ "mrr_at_1":0.8866396761133604,
148
+ "mrr_at_3":0.915991902834008,
149
+ "mrr_at_5":0.9190283400809716,
150
+ "mrr_at_10":0.9202091767881241,
151
+ "mrr_at_20":0.9207680541852368,
152
+ "mrr_at_50":0.9210783259706008,
153
+ "mrr_at_100":0.9211072444205719,
154
+ "naucs_at_1_max":0.6570120332617708,
155
+ "naucs_at_1_std":0.027148367339034946,
156
+ "naucs_at_1_diff1":0.954693725587737,
157
+ "naucs_at_3_max":0.8518572112090398,
158
+ "naucs_at_3_std":0.5033227123520332,
159
+ "naucs_at_3_diff1":0.9410604334985626,
160
+ "naucs_at_5_max":0.9198784015441375,
161
+ "naucs_at_5_std":0.6599441606302139,
162
+ "naucs_at_5_diff1":0.9628033833359825,
163
+ "naucs_at_10_max":0.9585432580086493,
164
+ "naucs_at_10_std":0.7697000086081518,
165
+ "naucs_at_10_diff1":1.0,
166
+ "naucs_at_20_max":0.9673496364838108,
167
+ "naucs_at_20_std":0.8687019487486011,
168
+ "naucs_at_20_diff1":1.0,
169
+ "naucs_at_50_max":0.9564661819783937,
170
+ "naucs_at_50_std":0.9319439680295378,
171
+ "naucs_at_50_diff1":1.0,
172
+ "naucs_at_100_max":0.9477594183740937,
173
+ "naucs_at_100_std":0.9183327616354471,
174
+ "naucs_at_100_diff1":1.0
175
+ },
176
+ "vidore/tabfquad_test_subsampled":{
177
+ "ndcg_at_1":0.89286,
178
+ "ndcg_at_3":0.93962,
179
+ "ndcg_at_5":0.94408,
180
+ "ndcg_at_10":0.94894,
181
+ "ndcg_at_20":0.94977,
182
+ "ndcg_at_50":0.94977,
183
+ "ndcg_at_100":0.94977,
184
+ "map_at_1":0.89286,
185
+ "map_at_3":0.92857,
186
+ "map_at_5":0.93107,
187
+ "map_at_10":0.93322,
188
+ "map_at_20":0.93341,
189
+ "map_at_50":0.93341,
190
+ "map_at_100":0.93341,
191
+ "recall_at_1":0.89286,
192
+ "recall_at_3":0.97143,
193
+ "recall_at_5":0.98214,
194
+ "recall_at_10":0.99643,
195
+ "recall_at_20":1.0,
196
+ "recall_at_50":1.0,
197
+ "recall_at_100":1.0,
198
+ "precision_at_1":0.89286,
199
+ "precision_at_3":0.32381,
200
+ "precision_at_5":0.19643,
201
+ "precision_at_10":0.09964,
202
+ "precision_at_20":0.05,
203
+ "precision_at_50":0.02,
204
+ "precision_at_100":0.01,
205
+ "mrr_at_1":0.8964285714285715,
206
+ "mrr_at_3":0.930952380952381,
207
+ "mrr_at_5":0.9336309523809524,
208
+ "mrr_at_10":0.9357780612244897,
209
+ "mrr_at_20":0.9359660311493018,
210
+ "mrr_at_50":0.9359660311493018,
211
+ "mrr_at_100":0.9359660311493018,
212
+ "naucs_at_1_max":0.589419152276295,
213
+ "naucs_at_1_std":0.25799058084772386,
214
+ "naucs_at_1_diff1":0.9168759811616957,
215
+ "naucs_at_3_max":0.8952497665732961,
216
+ "naucs_at_3_std":0.5145891690009315,
217
+ "naucs_at_3_diff1":0.8978758169934691,
218
+ "naucs_at_5_max":0.8585434173669502,
219
+ "naucs_at_5_std":0.6536881419234349,
220
+ "naucs_at_5_diff1":0.8627450980392123,
221
+ "naucs_at_10_max":1.0,
222
+ "naucs_at_10_std":1.0,
223
+ "naucs_at_10_diff1":0.72222222222224,
224
+ "naucs_at_20_max":1.0,
225
+ "naucs_at_20_std":1.0,
226
+ "naucs_at_20_diff1":1.0,
227
+ "naucs_at_50_max":1.0,
228
+ "naucs_at_50_std":1.0,
229
+ "naucs_at_50_diff1":1.0,
230
+ "naucs_at_100_max":1.0,
231
+ "naucs_at_100_std":1.0,
232
+ "naucs_at_100_diff1":1.0
233
+ },
234
+ "vidore/tatdqa_test":{
235
+ "ndcg_at_1":0.70717,
236
+ "ndcg_at_3":0.79456,
237
+ "ndcg_at_5":0.81297,
238
+ "ndcg_at_10":0.82424,
239
+ "ndcg_at_20":0.82919,
240
+ "ndcg_at_50":0.83284,
241
+ "ndcg_at_100":0.83523,
242
+ "map_at_1":0.70717,
243
+ "map_at_3":0.77329,
244
+ "map_at_5":0.78359,
245
+ "map_at_10":0.7884,
246
+ "map_at_20":0.78977,
247
+ "map_at_50":0.79038,
248
+ "map_at_100":0.79059,
249
+ "recall_at_1":0.70717,
250
+ "recall_at_3":0.85601,
251
+ "recall_at_5":0.90036,
252
+ "recall_at_10":0.93439,
253
+ "recall_at_20":0.95383,
254
+ "recall_at_50":0.97205,
255
+ "recall_at_100":0.98663,
256
+ "precision_at_1":0.70717,
257
+ "precision_at_3":0.28534,
258
+ "precision_at_5":0.18007,
259
+ "precision_at_10":0.09344,
260
+ "precision_at_20":0.04769,
261
+ "precision_at_50":0.01944,
262
+ "precision_at_100":0.00987,
263
+ "mrr_at_1":0.7023086269744836,
264
+ "mrr_at_3":0.7717699473471039,
265
+ "mrr_at_5":0.7816727420008102,
266
+ "mrr_at_10":0.7864732203128313,
267
+ "mrr_at_20":0.787759657888834,
268
+ "mrr_at_50":0.788430475412044,
269
+ "mrr_at_100":0.7886237843491343,
270
+ "naucs_at_1_max":0.1976745629949593,
271
+ "naucs_at_1_std":-0.07020091579321315,
272
+ "naucs_at_1_diff1":0.8341074480907863,
273
+ "naucs_at_3_max":0.2739593664910223,
274
+ "naucs_at_3_std":0.09719421770368855,
275
+ "naucs_at_3_diff1":0.733605301953241,
276
+ "naucs_at_5_max":0.28947443709217946,
277
+ "naucs_at_5_std":0.1533000171315339,
278
+ "naucs_at_5_diff1":0.6900117830352311,
279
+ "naucs_at_10_max":0.3583991399796331,
280
+ "naucs_at_10_std":0.24841173509752057,
281
+ "naucs_at_10_diff1":0.6368724254679143,
282
+ "naucs_at_20_max":0.3998152332693893,
283
+ "naucs_at_20_std":0.40035275451656677,
284
+ "naucs_at_20_diff1":0.5848768162171684,
285
+ "naucs_at_50_max":0.42687513985337017,
286
+ "naucs_at_50_std":0.41022440172224445,
287
+ "naucs_at_50_diff1":0.6184924487522029,
288
+ "naucs_at_100_max":0.48239198753920115,
289
+ "naucs_at_100_std":0.5542709753617254,
290
+ "naucs_at_100_diff1":0.6801547390328168
291
+ },
292
+ "vidore/shiftproject_test":{
293
+ "ndcg_at_1":0.83,
294
+ "ndcg_at_3":0.90309,
295
+ "ndcg_at_5":0.91083,
296
+ "ndcg_at_10":0.91439,
297
+ "ndcg_at_20":0.91718,
298
+ "ndcg_at_50":0.91902,
299
+ "ndcg_at_100":0.91902,
300
+ "map_at_1":0.83,
301
+ "map_at_3":0.88667,
302
+ "map_at_5":0.89067,
303
+ "map_at_10":0.89233,
304
+ "map_at_20":0.89324,
305
+ "map_at_50":0.89348,
306
+ "map_at_100":0.89348,
307
+ "recall_at_1":0.83,
308
+ "recall_at_3":0.95,
309
+ "recall_at_5":0.97,
310
+ "recall_at_10":0.98,
311
+ "recall_at_20":0.99,
312
+ "recall_at_50":1.0,
313
+ "recall_at_100":1.0,
314
+ "precision_at_1":0.83,
315
+ "precision_at_3":0.31667,
316
+ "precision_at_5":0.194,
317
+ "precision_at_10":0.098,
318
+ "precision_at_20":0.0495,
319
+ "precision_at_50":0.02,
320
+ "precision_at_100":0.01,
321
+ "mrr_at_1":0.82,
322
+ "mrr_at_3":0.885,
323
+ "mrr_at_5":0.887,
324
+ "mrr_at_10":0.8886666666666666,
325
+ "mrr_at_20":0.8895757575757576,
326
+ "mrr_at_50":0.8898138528138527,
327
+ "mrr_at_100":0.8898138528138527,
328
+ "naucs_at_1_max":0.06597202066523537,
329
+ "naucs_at_1_std":-0.5197074360016254,
330
+ "naucs_at_1_diff1":0.6896441632321363,
331
+ "naucs_at_3_max":0.2547152194211014,
332
+ "naucs_at_3_std":-0.7438842203548043,
333
+ "naucs_at_3_diff1":0.7722689075630248,
334
+ "naucs_at_5_max":0.3225957049486489,
335
+ "naucs_at_5_std":-0.7791783380018631,
336
+ "naucs_at_5_diff1":0.9128540305010848,
337
+ "naucs_at_10_max":0.42250233426704475,
338
+ "naucs_at_10_std":-0.2987861811391239,
339
+ "naucs_at_10_diff1":0.8692810457516353,
340
+ "naucs_at_20_max":0.7222222222222276,
341
+ "naucs_at_20_std":0.5541549953314738,
342
+ "naucs_at_20_diff1":0.8692810457516413,
343
+ "naucs_at_50_max":null,
344
+ "naucs_at_50_std":null,
345
+ "naucs_at_50_diff1":null,
346
+ "naucs_at_100_max":null,
347
+ "naucs_at_100_std":null,
348
+ "naucs_at_100_diff1":null
349
+ },
350
+ "vidore/syntheticDocQA_artificial_intelligence_test":{
351
+ "ndcg_at_1":0.96,
352
+ "ndcg_at_3":0.97893,
353
+ "ndcg_at_5":0.97893,
354
+ "ndcg_at_10":0.98249,
355
+ "ndcg_at_20":0.98249,
356
+ "ndcg_at_50":0.98249,
357
+ "ndcg_at_100":0.98249,
358
+ "map_at_1":0.96,
359
+ "map_at_3":0.975,
360
+ "map_at_5":0.975,
361
+ "map_at_10":0.97667,
362
+ "map_at_20":0.97667,
363
+ "map_at_50":0.97667,
364
+ "map_at_100":0.97667,
365
+ "recall_at_1":0.96,
366
+ "recall_at_3":0.99,
367
+ "recall_at_5":0.99,
368
+ "recall_at_10":1.0,
369
+ "recall_at_20":1.0,
370
+ "recall_at_50":1.0,
371
+ "recall_at_100":1.0,
372
+ "precision_at_1":0.96,
373
+ "precision_at_3":0.33,
374
+ "precision_at_5":0.198,
375
+ "precision_at_10":0.1,
376
+ "precision_at_20":0.05,
377
+ "precision_at_50":0.02,
378
+ "precision_at_100":0.01,
379
+ "mrr_at_1":0.98,
380
+ "mrr_at_3":0.985,
381
+ "mrr_at_5":0.985,
382
+ "mrr_at_10":0.9866666666666667,
383
+ "mrr_at_20":0.9866666666666667,
384
+ "mrr_at_50":0.9866666666666667,
385
+ "mrr_at_100":0.9866666666666667,
386
+ "naucs_at_1_max":0.3437208216620012,
387
+ "naucs_at_1_std":-0.1860410830999054,
388
+ "naucs_at_1_diff1":1.0,
389
+ "naucs_at_3_max":0.8692810457516356,
390
+ "naucs_at_3_std":-0.5634920634921204,
391
+ "naucs_at_3_diff1":1.0,
392
+ "naucs_at_5_max":0.8692810457516413,
393
+ "naucs_at_5_std":-0.5634920634920767,
394
+ "naucs_at_5_diff1":1.0,
395
+ "naucs_at_10_max":1.0,
396
+ "naucs_at_10_std":1.0,
397
+ "naucs_at_10_diff1":1.0,
398
+ "naucs_at_20_max":1.0,
399
+ "naucs_at_20_std":1.0,
400
+ "naucs_at_20_diff1":1.0,
401
+ "naucs_at_50_max":null,
402
+ "naucs_at_50_std":null,
403
+ "naucs_at_50_diff1":null,
404
+ "naucs_at_100_max":null,
405
+ "naucs_at_100_std":null,
406
+ "naucs_at_100_diff1":null
407
+ },
408
+ "vidore/syntheticDocQA_energy_test":{
409
+ "ndcg_at_1":0.93,
410
+ "ndcg_at_3":0.96024,
411
+ "ndcg_at_5":0.96024,
412
+ "ndcg_at_10":0.96339,
413
+ "ndcg_at_20":0.96618,
414
+ "ndcg_at_50":0.96618,
415
+ "ndcg_at_100":0.96618,
416
+ "map_at_1":0.93,
417
+ "map_at_3":0.95333,
418
+ "map_at_5":0.95333,
419
+ "map_at_10":0.95458,
420
+ "map_at_20":0.95549,
421
+ "map_at_50":0.95549,
422
+ "map_at_100":0.95549,
423
+ "recall_at_1":0.93,
424
+ "recall_at_3":0.98,
425
+ "recall_at_5":0.98,
426
+ "recall_at_10":0.99,
427
+ "recall_at_20":1.0,
428
+ "recall_at_50":1.0,
429
+ "recall_at_100":1.0,
430
+ "precision_at_1":0.93,
431
+ "precision_at_3":0.32667,
432
+ "precision_at_5":0.196,
433
+ "precision_at_10":0.099,
434
+ "precision_at_20":0.05,
435
+ "precision_at_50":0.02,
436
+ "precision_at_100":0.01,
437
+ "mrr_at_1":0.94,
438
+ "mrr_at_3":0.9583333333333333,
439
+ "mrr_at_5":0.9583333333333333,
440
+ "mrr_at_10":0.960873015873016,
441
+ "mrr_at_20":0.960873015873016,
442
+ "mrr_at_50":0.960873015873016,
443
+ "mrr_at_100":0.960873015873016,
444
+ "naucs_at_1_max":0.6919434440442851,
445
+ "naucs_at_1_std":-0.4906629318394028,
446
+ "naucs_at_1_diff1":0.9813258636788056,
447
+ "naucs_at_3_max":0.7117180205415458,
448
+ "naucs_at_3_std":-1.4458450046685478,
449
+ "naucs_at_3_diff1":1.0,
450
+ "naucs_at_5_max":0.7117180205415541,
451
+ "naucs_at_5_std":-1.445845004668519,
452
+ "naucs_at_5_diff1":1.0,
453
+ "naucs_at_10_max":0.8692810457516413,
454
+ "naucs_at_10_std":-1.1517273576097316,
455
+ "naucs_at_10_diff1":1.0,
456
+ "naucs_at_20_max":1.0,
457
+ "naucs_at_20_std":1.0,
458
+ "naucs_at_20_diff1":1.0,
459
+ "naucs_at_50_max":null,
460
+ "naucs_at_50_std":null,
461
+ "naucs_at_50_diff1":null,
462
+ "naucs_at_100_max":null,
463
+ "naucs_at_100_std":null,
464
+ "naucs_at_100_diff1":null
465
+ },
466
+ "vidore/syntheticDocQA_government_reports_test":{
467
+ "ndcg_at_1":0.94,
468
+ "ndcg_at_3":0.97655,
469
+ "ndcg_at_5":0.97655,
470
+ "ndcg_at_10":0.97655,
471
+ "ndcg_at_20":0.97655,
472
+ "ndcg_at_50":0.97655,
473
+ "ndcg_at_100":0.97655,
474
+ "map_at_1":0.94,
475
+ "map_at_3":0.96833,
476
+ "map_at_5":0.96833,
477
+ "map_at_10":0.96833,
478
+ "map_at_20":0.96833,
479
+ "map_at_50":0.96833,
480
+ "map_at_100":0.96833,
481
+ "recall_at_1":0.94,
482
+ "recall_at_3":1.0,
483
+ "recall_at_5":1.0,
484
+ "recall_at_10":1.0,
485
+ "recall_at_20":1.0,
486
+ "recall_at_50":1.0,
487
+ "recall_at_100":1.0,
488
+ "precision_at_1":0.94,
489
+ "precision_at_3":0.33333,
490
+ "precision_at_5":0.2,
491
+ "precision_at_10":0.1,
492
+ "precision_at_20":0.05,
493
+ "precision_at_50":0.02,
494
+ "precision_at_100":0.01,
495
+ "mrr_at_1":0.96,
496
+ "mrr_at_3":0.975,
497
+ "mrr_at_5":0.9775,
498
+ "mrr_at_10":0.9775,
499
+ "mrr_at_20":0.9775,
500
+ "mrr_at_50":0.9775,
501
+ "mrr_at_100":0.9775,
502
+ "naucs_at_1_max":0.7468098350451301,
503
+ "naucs_at_1_std":0.40919701213818827,
504
+ "naucs_at_1_diff1":0.9782135076252712,
505
+ "naucs_at_3_max":1.0,
506
+ "naucs_at_3_std":1.0,
507
+ "naucs_at_3_diff1":1.0,
508
+ "naucs_at_5_max":1.0,
509
+ "naucs_at_5_std":1.0,
510
+ "naucs_at_5_diff1":1.0,
511
+ "naucs_at_10_max":1.0,
512
+ "naucs_at_10_std":1.0,
513
+ "naucs_at_10_diff1":1.0,
514
+ "naucs_at_20_max":1.0,
515
+ "naucs_at_20_std":1.0,
516
+ "naucs_at_20_diff1":1.0,
517
+ "naucs_at_50_max":null,
518
+ "naucs_at_50_std":null,
519
+ "naucs_at_50_diff1":null,
520
+ "naucs_at_100_max":null,
521
+ "naucs_at_100_std":null,
522
+ "naucs_at_100_diff1":null
523
+ },
524
+ "vidore/syntheticDocQA_healthcare_industry_test":{
525
+ "ndcg_at_1":0.97,
526
+ "ndcg_at_3":0.98893,
527
+ "ndcg_at_5":0.98893,
528
+ "ndcg_at_10":0.98893,
529
+ "ndcg_at_20":0.98893,
530
+ "ndcg_at_50":0.98893,
531
+ "ndcg_at_100":0.98893,
532
+ "map_at_1":0.97,
533
+ "map_at_3":0.985,
534
+ "map_at_5":0.985,
535
+ "map_at_10":0.985,
536
+ "map_at_20":0.985,
537
+ "map_at_50":0.985,
538
+ "map_at_100":0.985,
539
+ "recall_at_1":0.97,
540
+ "recall_at_3":1.0,
541
+ "recall_at_5":1.0,
542
+ "recall_at_10":1.0,
543
+ "recall_at_20":1.0,
544
+ "recall_at_50":1.0,
545
+ "recall_at_100":1.0,
546
+ "precision_at_1":0.97,
547
+ "precision_at_3":0.33333,
548
+ "precision_at_5":0.2,
549
+ "precision_at_10":0.1,
550
+ "precision_at_20":0.05,
551
+ "precision_at_50":0.02,
552
+ "precision_at_100":0.01,
553
+ "mrr_at_1":0.97,
554
+ "mrr_at_3":0.985,
555
+ "mrr_at_5":0.985,
556
+ "mrr_at_10":0.985,
557
+ "mrr_at_20":0.985,
558
+ "mrr_at_50":0.985,
559
+ "mrr_at_100":0.985,
560
+ "naucs_at_1_max":0.5938375350140056,
561
+ "naucs_at_1_std":-0.1512605042016779,
562
+ "naucs_at_1_diff1":1.0,
563
+ "naucs_at_3_max":1.0,
564
+ "naucs_at_3_std":1.0,
565
+ "naucs_at_3_diff1":1.0,
566
+ "naucs_at_5_max":1.0,
567
+ "naucs_at_5_std":1.0,
568
+ "naucs_at_5_diff1":1.0,
569
+ "naucs_at_10_max":1.0,
570
+ "naucs_at_10_std":1.0,
571
+ "naucs_at_10_diff1":1.0,
572
+ "naucs_at_20_max":1.0,
573
+ "naucs_at_20_std":1.0,
574
+ "naucs_at_20_diff1":1.0,
575
+ "naucs_at_50_max":null,
576
+ "naucs_at_50_std":null,
577
+ "naucs_at_50_diff1":null,
578
+ "naucs_at_100_max":null,
579
+ "naucs_at_100_std":null,
580
+ "naucs_at_100_diff1":null
581
+ },
582
+ "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered":{
583
+ "ndcg_at_1":0.6,
584
+ "ndcg_at_3":0.6151,
585
+ "ndcg_at_5":0.63545,
586
+ "ndcg_at_10":0.67291,
587
+ "ndcg_at_20":0.69552,
588
+ "ndcg_at_50":0.71505,
589
+ "ndcg_at_100":0.72644,
590
+ "map_at_1":0.36564,
591
+ "map_at_3":0.49748,
592
+ "map_at_5":0.53983,
593
+ "map_at_10":0.57966,
594
+ "map_at_20":0.59407,
595
+ "map_at_50":0.60166,
596
+ "map_at_100":0.60419,
597
+ "recall_at_1":0.36564,
598
+ "recall_at_3":0.57915,
599
+ "recall_at_5":0.6723,
600
+ "recall_at_10":0.7796,
601
+ "recall_at_20":0.83839,
602
+ "recall_at_50":0.89828,
603
+ "recall_at_100":0.94039,
604
+ "precision_at_1":0.6,
605
+ "precision_at_3":0.38333,
606
+ "precision_at_5":0.28875,
607
+ "precision_at_10":0.18688,
608
+ "precision_at_20":0.10906,
609
+ "precision_at_50":0.05037,
610
+ "precision_at_100":0.02756,
611
+ "mrr_at_1":0.6125,
612
+ "mrr_at_3":0.7114583333333332,
613
+ "mrr_at_5":0.7258333333333333,
614
+ "mrr_at_10":0.7311706349206349,
615
+ "mrr_at_20":0.7328478057889821,
616
+ "mrr_at_50":0.7335337032248797,
617
+ "mrr_at_100":0.7337362495211759,
618
+ "naucs_at_1_max":0.3196794300979519,
619
+ "naucs_at_1_std":-0.06999480558029103,
620
+ "naucs_at_1_diff1":0.46354630454140655,
621
+ "naucs_at_3_max":-0.024028225250570488,
622
+ "naucs_at_3_std":-0.0772467105431113,
623
+ "naucs_at_3_diff1":-0.13384017605040516,
624
+ "naucs_at_5_max":-0.1107018755412317,
625
+ "naucs_at_5_std":-0.13468600304734307,
626
+ "naucs_at_5_diff1":-0.1913870528096573,
627
+ "naucs_at_10_max":-0.15104624102495343,
628
+ "naucs_at_10_std":-0.11990214904902942,
629
+ "naucs_at_10_diff1":-0.27309446189419934,
630
+ "naucs_at_20_max":-0.1510467527515919,
631
+ "naucs_at_20_std":-0.05158870650850273,
632
+ "naucs_at_20_diff1":-0.2855800617041388,
633
+ "naucs_at_50_max":-0.189407669514686,
634
+ "naucs_at_50_std":0.011655782821744832,
635
+ "naucs_at_50_diff1":-0.29769313630537414,
636
+ "naucs_at_100_max":-0.22560114991297742,
637
+ "naucs_at_100_std":0.03455222954387382,
638
+ "naucs_at_100_diff1":-0.29629886192096655
639
+ },
640
+ "vidore/synthetic_economics_macro_economy_2024_filtered_v1.0":{
641
+ "ndcg_at_1":0.62069,
642
+ "ndcg_at_3":0.61762,
643
+ "ndcg_at_5":0.60225,
644
+ "ndcg_at_10":0.58048,
645
+ "ndcg_at_20":0.61347,
646
+ "ndcg_at_50":0.67491,
647
+ "ndcg_at_100":0.71101,
648
+ "map_at_1":0.09096,
649
+ "map_at_3":0.20035,
650
+ "map_at_5":0.26381,
651
+ "map_at_10":0.33202,
652
+ "map_at_20":0.39844,
653
+ "map_at_50":0.45746,
654
+ "map_at_100":0.48541,
655
+ "recall_at_1":0.09096,
656
+ "recall_at_3":0.24139,
657
+ "recall_at_5":0.33438,
658
+ "recall_at_10":0.4587,
659
+ "recall_at_20":0.62591,
660
+ "recall_at_50":0.81242,
661
+ "recall_at_100":0.91777,
662
+ "precision_at_1":0.62069,
663
+ "precision_at_3":0.57471,
664
+ "precision_at_5":0.53448,
665
+ "precision_at_10":0.42414,
666
+ "precision_at_20":0.32672,
667
+ "precision_at_50":0.19759,
668
+ "precision_at_100":0.12862,
669
+ "mrr_at_1":0.603448275862069,
670
+ "mrr_at_3":0.7241379310344828,
671
+ "mrr_at_5":0.7405172413793104,
672
+ "mrr_at_10":0.7462643678160921,
673
+ "mrr_at_20":0.7475906277630417,
674
+ "mrr_at_50":0.7484116458254391,
675
+ "mrr_at_100":0.7484116458254391,
676
+ "naucs_at_1_max":0.18510409805228442,
677
+ "naucs_at_1_std":0.35494696439734424,
678
+ "naucs_at_1_diff1":0.16217400181533045,
679
+ "naucs_at_3_max":0.11476072335324272,
680
+ "naucs_at_3_std":0.14220252935282734,
681
+ "naucs_at_3_diff1":0.20624608835397928,
682
+ "naucs_at_5_max":0.05768772419881633,
683
+ "naucs_at_5_std":0.06310746641396357,
684
+ "naucs_at_5_diff1":0.18987051287290022,
685
+ "naucs_at_10_max":0.0985016982729016,
686
+ "naucs_at_10_std":0.20584586715310207,
687
+ "naucs_at_10_diff1":0.06505841014753395,
688
+ "naucs_at_20_max":0.08004110479748268,
689
+ "naucs_at_20_std":0.287577784204017,
690
+ "naucs_at_20_diff1":0.020551986645709248,
691
+ "naucs_at_50_max":0.014573240638718194,
692
+ "naucs_at_50_std":0.24605332511304584,
693
+ "naucs_at_50_diff1":-0.020387827810068312,
694
+ "naucs_at_100_max":-0.05010509973449726,
695
+ "naucs_at_100_std":0.1897950634215769,
696
+ "naucs_at_100_diff1":-0.014466845102017144
697
+ },
698
+ "vidore/synthetic_rse_restaurant_filtered_v1.0":{
699
+ "ndcg_at_1":0.52632,
700
+ "ndcg_at_3":0.55585,
701
+ "ndcg_at_5":0.56608,
702
+ "ndcg_at_10":0.60595,
703
+ "ndcg_at_20":0.63951,
704
+ "ndcg_at_50":0.67486,
705
+ "ndcg_at_100":0.68663,
706
+ "map_at_1":0.18937,
707
+ "map_at_3":0.38648,
708
+ "map_at_5":0.42924,
709
+ "map_at_10":0.4756,
710
+ "map_at_20":0.49684,
711
+ "map_at_50":0.51563,
712
+ "map_at_100":0.52215,
713
+ "recall_at_1":0.18937,
714
+ "recall_at_3":0.52147,
715
+ "recall_at_5":0.61387,
716
+ "recall_at_10":0.7448,
717
+ "recall_at_20":0.84958,
718
+ "recall_at_50":0.95384,
719
+ "recall_at_100":0.98246,
720
+ "precision_at_1":0.52632,
721
+ "precision_at_3":0.40351,
722
+ "precision_at_5":0.29825,
723
+ "precision_at_10":0.2,
724
+ "precision_at_20":0.12632,
725
+ "precision_at_50":0.06842,
726
+ "precision_at_100":0.03877,
727
+ "mrr_at_1":0.5263157894736842,
728
+ "mrr_at_3":0.6608187134502922,
729
+ "mrr_at_5":0.6687134502923976,
730
+ "mrr_at_10":0.6770676691729323,
731
+ "mrr_at_20":0.6805936409651578,
732
+ "mrr_at_50":0.6813246351172046,
733
+ "mrr_at_100":0.6813246351172046,
734
+ "naucs_at_1_max":-0.3657070379375877,
735
+ "naucs_at_1_std":-0.2598454613027199,
736
+ "naucs_at_1_diff1":0.20497205438323887,
737
+ "naucs_at_3_max":-0.2760768601040555,
738
+ "naucs_at_3_std":-0.19536511254108982,
739
+ "naucs_at_3_diff1":0.12639737194669312,
740
+ "naucs_at_5_max":-0.32266979804661855,
741
+ "naucs_at_5_std":-0.2321273259469018,
742
+ "naucs_at_5_diff1":0.12201056497848635,
743
+ "naucs_at_10_max":-0.31327785677716363,
744
+ "naucs_at_10_std":-0.20701857432203374,
745
+ "naucs_at_10_diff1":0.12714449010861775,
746
+ "naucs_at_20_max":-0.3057758145014666,
747
+ "naucs_at_20_std":-0.19196155860715694,
748
+ "naucs_at_20_diff1":0.004456792889016827,
749
+ "naucs_at_50_max":-0.3443751963336487,
750
+ "naucs_at_50_std":-0.19916004962508968,
751
+ "naucs_at_50_diff1":-0.15313050707770795,
752
+ "naucs_at_100_max":-0.33335268769256254,
753
+ "naucs_at_100_std":-0.1759902263556841,
754
+ "naucs_at_100_diff1":-0.16546750884331984
755
+ },
756
+ "vidore/synthetic_axa_filtered_v1.0":{
757
+ "ndcg_at_1":0.72222,
758
+ "ndcg_at_3":0.68859,
759
+ "ndcg_at_5":0.6877,
760
+ "ndcg_at_10":0.69829,
761
+ "ndcg_at_20":0.7342,
762
+ "ndcg_at_50":0.77785,
763
+ "ndcg_at_100":0.78996,
764
+ "map_at_1":0.36488,
765
+ "map_at_3":0.46953,
766
+ "map_at_5":0.52392,
767
+ "map_at_10":0.58858,
768
+ "map_at_20":0.62889,
769
+ "map_at_50":0.64917,
770
+ "map_at_100":0.65352,
771
+ "recall_at_1":0.36488,
772
+ "recall_at_3":0.54323,
773
+ "recall_at_5":0.61414,
774
+ "recall_at_10":0.71635,
775
+ "recall_at_20":0.82542,
776
+ "recall_at_50":0.95323,
777
+ "recall_at_100":0.98765,
778
+ "precision_at_1":0.72222,
779
+ "precision_at_3":0.44444,
780
+ "precision_at_5":0.37778,
781
+ "precision_at_10":0.27222,
782
+ "precision_at_20":0.175,
783
+ "precision_at_50":0.08667,
784
+ "precision_at_100":0.04667,
785
+ "mrr_at_1":0.6111111111111112,
786
+ "mrr_at_3":0.7592592592592592,
787
+ "mrr_at_5":0.7592592592592592,
788
+ "mrr_at_10":0.7592592592592592,
789
+ "mrr_at_20":0.7592592592592592,
790
+ "mrr_at_50":0.7611111111111111,
791
+ "mrr_at_100":0.7611111111111111,
792
+ "naucs_at_1_max":-0.1072500882788756,
793
+ "naucs_at_1_std":-0.07848008527574335,
794
+ "naucs_at_1_diff1":0.3888329697673727,
795
+ "naucs_at_3_max":-0.5668751047952342,
796
+ "naucs_at_3_std":-0.5329585384567367,
797
+ "naucs_at_3_diff1":-0.2021392643633502,
798
+ "naucs_at_5_max":-0.5633098595994385,
799
+ "naucs_at_5_std":-0.43232123457673266,
800
+ "naucs_at_5_diff1":-0.17951311814925686,
801
+ "naucs_at_10_max":-0.6374122831555527,
802
+ "naucs_at_10_std":-0.43175557593234065,
803
+ "naucs_at_10_diff1":-0.31039799211753494,
804
+ "naucs_at_20_max":-0.701465591207169,
805
+ "naucs_at_20_std":-0.4917500935922029,
806
+ "naucs_at_20_diff1":-0.35064529361083185,
807
+ "naucs_at_50_max":-0.7021744453459953,
808
+ "naucs_at_50_std":-0.4855377059097475,
809
+ "naucs_at_50_diff1":-0.36456623920339126,
810
+ "naucs_at_100_max":-0.6924863874111336,
811
+ "naucs_at_100_std":-0.4863559555556065,
812
+ "naucs_at_100_diff1":-0.3608886108131484
813
+ },
814
+ "vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual":{
815
+ "ndcg_at_1":0.54386,
816
+ "ndcg_at_3":0.53992,
817
+ "ndcg_at_5":0.57161,
818
+ "ndcg_at_10":0.61517,
819
+ "ndcg_at_20":0.64796,
820
+ "ndcg_at_50":0.67915,
821
+ "ndcg_at_100":0.69235,
822
+ "map_at_1":0.22592,
823
+ "map_at_3":0.38229,
824
+ "map_at_5":0.43639,
825
+ "map_at_10":0.48456,
826
+ "map_at_20":0.50644,
827
+ "map_at_50":0.52393,
828
+ "map_at_100":0.53044,
829
+ "recall_at_1":0.22592,
830
+ "recall_at_3":0.48555,
831
+ "recall_at_5":0.61365,
832
+ "recall_at_10":0.75902,
833
+ "recall_at_20":0.86188,
834
+ "recall_at_50":0.94857,
835
+ "recall_at_100":0.98684,
836
+ "precision_at_1":0.54386,
837
+ "precision_at_3":0.3845,
838
+ "precision_at_5":0.30351,
839
+ "precision_at_10":0.20439,
840
+ "precision_at_20":0.12785,
841
+ "precision_at_50":0.06851,
842
+ "precision_at_100":0.03882,
843
+ "mrr_at_1":0.5394736842105263,
844
+ "mrr_at_3":0.6491228070175438,
845
+ "mrr_at_5":0.6675438596491228,
846
+ "mrr_at_10":0.6769945697577275,
847
+ "mrr_at_20":0.6792236734283947,
848
+ "mrr_at_50":0.6797428454113825,
849
+ "mrr_at_100":0.6798197921642295,
850
+ "naucs_at_1_max":-0.20674277350895354,
851
+ "naucs_at_1_std":-0.12027303922549912,
852
+ "naucs_at_1_diff1":0.23775810754837193,
853
+ "naucs_at_3_max":-0.14132383047647284,
854
+ "naucs_at_3_std":-0.11240148832069007,
855
+ "naucs_at_3_diff1":0.15033788234126377,
856
+ "naucs_at_5_max":-0.17140084599390548,
857
+ "naucs_at_5_std":-0.13104605490168167,
858
+ "naucs_at_5_diff1":0.1523799082346645,
859
+ "naucs_at_10_max":-0.17604422702000652,
860
+ "naucs_at_10_std":-0.1040197021731718,
861
+ "naucs_at_10_diff1":0.141987374687683,
862
+ "naucs_at_20_max":-0.18707526779473269,
863
+ "naucs_at_20_std":-0.05659957021660996,
864
+ "naucs_at_20_diff1":0.043138658571222205,
865
+ "naucs_at_50_max":-0.23552302035441924,
866
+ "naucs_at_50_std":-0.05397637299883905,
867
+ "naucs_at_50_diff1":-0.09007005759845056,
868
+ "naucs_at_100_max":-0.2339022131728518,
869
+ "naucs_at_100_std":-0.0193642217972453,
870
+ "naucs_at_100_diff1":-0.11400444827044932
871
+ },
872
+ "vidore/synthetic_axa_filtered_v1.0_multilingual":{
873
+ "ndcg_at_1":0.63889,
874
+ "ndcg_at_3":0.62281,
875
+ "ndcg_at_5":0.60952,
876
+ "ndcg_at_10":0.64318,
877
+ "ndcg_at_20":0.67634,
878
+ "ndcg_at_50":0.71094,
879
+ "ndcg_at_100":0.72844,
880
+ "map_at_1":0.32704,
881
+ "map_at_3":0.41888,
882
+ "map_at_5":0.46563,
883
+ "map_at_10":0.53051,
884
+ "map_at_20":0.56674,
885
+ "map_at_50":0.58314,
886
+ "map_at_100":0.58783,
887
+ "recall_at_1":0.32704,
888
+ "recall_at_3":0.48365,
889
+ "recall_at_5":0.54387,
890
+ "recall_at_10":0.69125,
891
+ "recall_at_20":0.78669,
892
+ "recall_at_50":0.8863,
893
+ "recall_at_100":0.9429,
894
+ "precision_at_1":0.63889,
895
+ "precision_at_3":0.41204,
896
+ "precision_at_5":0.33333,
897
+ "precision_at_10":0.25417,
898
+ "precision_at_20":0.16597,
899
+ "precision_at_50":0.07972,
900
+ "precision_at_100":0.04431,
901
+ "mrr_at_1":0.5972222222222222,
902
+ "mrr_at_3":0.7083333333333333,
903
+ "mrr_at_5":0.7083333333333333,
904
+ "mrr_at_10":0.7178791887125221,
905
+ "mrr_at_20":0.7191418149751484,
906
+ "mrr_at_50":0.7199862392542369,
907
+ "mrr_at_100":0.7201556159480039,
908
+ "naucs_at_1_max":0.11301406077201734,
909
+ "naucs_at_1_std":0.21519921250929616,
910
+ "naucs_at_1_diff1":0.3601399303857268,
911
+ "naucs_at_3_max":-0.24927986503179209,
912
+ "naucs_at_3_std":-0.09022708366608238,
913
+ "naucs_at_3_diff1":0.04489545233674075,
914
+ "naucs_at_5_max":-0.26591050096906066,
915
+ "naucs_at_5_std":-0.07265537709306702,
916
+ "naucs_at_5_diff1":0.0014191239058859906,
917
+ "naucs_at_10_max":-0.3903220005756808,
918
+ "naucs_at_10_std":-0.12521844950880665,
919
+ "naucs_at_10_diff1":-0.19712230727571253,
920
+ "naucs_at_20_max":-0.45199817313888363,
921
+ "naucs_at_20_std":-0.1484667347150115,
922
+ "naucs_at_20_diff1":-0.2608757999232997,
923
+ "naucs_at_50_max":-0.48614207326501946,
924
+ "naucs_at_50_std":-0.15554359778230578,
925
+ "naucs_at_50_diff1":-0.27852375257122247,
926
+ "naucs_at_100_max":-0.5125082706318165,
927
+ "naucs_at_100_std":-0.18550458631758462,
928
+ "naucs_at_100_diff1":-0.31194041608707157
929
+ },
930
+ "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual":{
931
+ "ndcg_at_1":0.58125,
932
+ "ndcg_at_3":0.60975,
933
+ "ndcg_at_5":0.62539,
934
+ "ndcg_at_10":0.65521,
935
+ "ndcg_at_20":0.67922,
936
+ "ndcg_at_50":0.70341,
937
+ "ndcg_at_100":0.71315,
938
+ "map_at_1":0.35357,
939
+ "map_at_3":0.49223,
940
+ "map_at_5":0.5321,
941
+ "map_at_10":0.56549,
942
+ "map_at_20":0.5796,
943
+ "map_at_50":0.58865,
944
+ "map_at_100":0.59103,
945
+ "recall_at_1":0.35357,
946
+ "recall_at_3":0.57487,
947
+ "recall_at_5":0.65905,
948
+ "recall_at_10":0.7508,
949
+ "recall_at_20":0.81705,
950
+ "recall_at_50":0.89072,
951
+ "recall_at_100":0.92568,
952
+ "precision_at_1":0.58125,
953
+ "precision_at_3":0.3849,
954
+ "precision_at_5":0.28719,
955
+ "precision_at_10":0.18125,
956
+ "precision_at_20":0.10578,
957
+ "precision_at_50":0.05062,
958
+ "precision_at_100":0.02748,
959
+ "mrr_at_1":0.5796875,
960
+ "mrr_at_3":0.6901041666666663,
961
+ "mrr_at_5":0.7021354166666661,
962
+ "mrr_at_10":0.7074832589285712,
963
+ "mrr_at_20":0.7102574911812041,
964
+ "mrr_at_50":0.7110110149629919,
965
+ "mrr_at_100":0.7111676465392118,
966
+ "naucs_at_1_max":0.17241551553460638,
967
+ "naucs_at_1_std":-0.10458500213424893,
968
+ "naucs_at_1_diff1":0.5014939741528845,
969
+ "naucs_at_3_max":0.04213476105852452,
970
+ "naucs_at_3_std":-0.03593819184778826,
971
+ "naucs_at_3_diff1":-0.03987788271154801,
972
+ "naucs_at_5_max":0.027250565594662386,
973
+ "naucs_at_5_std":-0.037278236776539624,
974
+ "naucs_at_5_diff1":-0.1239404049371398,
975
+ "naucs_at_10_max":-0.06115387637712348,
976
+ "naucs_at_10_std":-0.0718804318785458,
977
+ "naucs_at_10_diff1":-0.19295981392132494,
978
+ "naucs_at_20_max":-0.09125226002964483,
979
+ "naucs_at_20_std":-0.028359299920185887,
980
+ "naucs_at_20_diff1":-0.22651248920886707,
981
+ "naucs_at_50_max":-0.10766546120682835,
982
+ "naucs_at_50_std":0.03593323121140819,
983
+ "naucs_at_50_diff1":-0.25675662871310556,
984
+ "naucs_at_100_max":-0.12997916463636278,
985
+ "naucs_at_100_std":0.05375545158818975,
986
+ "naucs_at_100_diff1":-0.2582624772102094
987
+ },
988
+ "vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual":{
989
+ "ndcg_at_1":0.57759,
990
+ "ndcg_at_3":0.57138,
991
+ "ndcg_at_5":0.55497,
992
+ "ndcg_at_10":0.5473,
993
+ "ndcg_at_20":0.58512,
994
+ "ndcg_at_50":0.65027,
995
+ "ndcg_at_100":0.68902,
996
+ "map_at_1":0.08005,
997
+ "map_at_3":0.17589,
998
+ "map_at_5":0.22976,
999
+ "map_at_10":0.29906,
1000
+ "map_at_20":0.36451,
1001
+ "map_at_50":0.42404,
1002
+ "map_at_100":0.45273,
1003
+ "recall_at_1":0.08005,
1004
+ "recall_at_3":0.21653,
1005
+ "recall_at_5":0.30793,
1006
+ "recall_at_10":0.43982,
1007
+ "recall_at_20":0.60961,
1008
+ "recall_at_50":0.80111,
1009
+ "recall_at_100":0.91548,
1010
+ "precision_at_1":0.57759,
1011
+ "precision_at_3":0.53592,
1012
+ "precision_at_5":0.49138,
1013
+ "precision_at_10":0.40733,
1014
+ "precision_at_20":0.31832,
1015
+ "precision_at_50":0.19638,
1016
+ "precision_at_100":0.12836,
1017
+ "mrr_at_1":0.5646551724137931,
1018
+ "mrr_at_3":0.694683908045977,
1019
+ "mrr_at_5":0.7136494252873563,
1020
+ "mrr_at_10":0.7207478106185002,
1021
+ "mrr_at_20":0.7223871734108802,
1022
+ "mrr_at_50":0.7225924279264796,
1023
+ "mrr_at_100":0.7225924279264796,
1024
+ "naucs_at_1_max":0.025825981954306243,
1025
+ "naucs_at_1_std":0.06786701290377438,
1026
+ "naucs_at_1_diff1":0.3119241048950317,
1027
+ "naucs_at_3_max":0.0479066957744716,
1028
+ "naucs_at_3_std":0.06557391489213844,
1029
+ "naucs_at_3_diff1":0.23439300856464848,
1030
+ "naucs_at_5_max":0.0517250332191857,
1031
+ "naucs_at_5_std":0.09464648925799282,
1032
+ "naucs_at_5_diff1":0.2254037385021122,
1033
+ "naucs_at_10_max":0.07385165346450225,
1034
+ "naucs_at_10_std":0.14105623461417685,
1035
+ "naucs_at_10_diff1":0.09658147605174039,
1036
+ "naucs_at_20_max":0.04903637832153811,
1037
+ "naucs_at_20_std":0.1590552355815479,
1038
+ "naucs_at_20_diff1":0.028107412938548966,
1039
+ "naucs_at_50_max":0.02938750541507763,
1040
+ "naucs_at_50_std":0.15805354436493257,
1041
+ "naucs_at_50_diff1":-0.04958795351145276,
1042
+ "naucs_at_100_max":-0.0034893431750791983,
1043
+ "naucs_at_100_std":0.13285693605908278,
1044
+ "naucs_at_100_diff1":-0.07289241471567467
1045
+ },
1046
+ "vidore/restaurant_esg_reports_beir":{
1047
+ "ndcg_at_1":0.66667,
1048
+ "ndcg_at_3":0.62961,
1049
+ "ndcg_at_5":0.65844,
1050
+ "ndcg_at_10":0.70149,
1051
+ "ndcg_at_20":0.72887,
1052
+ "ndcg_at_50":0.75185,
1053
+ "ndcg_at_100":0.75669,
1054
+ "map_at_1":0.47262,
1055
+ "map_at_3":0.55789,
1056
+ "map_at_5":0.59623,
1057
+ "map_at_10":0.62874,
1058
+ "map_at_20":0.64199,
1059
+ "map_at_50":0.64885,
1060
+ "map_at_100":0.65059,
1061
+ "recall_at_1":0.47262,
1062
+ "recall_at_3":0.58302,
1063
+ "recall_at_5":0.68751,
1064
+ "recall_at_10":0.8013,
1065
+ "recall_at_20":0.88308,
1066
+ "recall_at_50":0.9586,
1067
+ "recall_at_100":0.97619,
1068
+ "precision_at_1":0.69231,
1069
+ "precision_at_3":0.33974,
1070
+ "precision_at_5":0.24615,
1071
+ "precision_at_10":0.15577,
1072
+ "precision_at_20":0.09231,
1073
+ "precision_at_50":0.04269,
1074
+ "precision_at_100":0.02288,
1075
+ "mrr_at_1":0.6923076923076923,
1076
+ "mrr_at_3":0.7371794871794872,
1077
+ "mrr_at_5":0.7583333333333333,
1078
+ "mrr_at_10":0.7666666666666665,
1079
+ "mrr_at_20":0.7698942083557468,
1080
+ "mrr_at_50":0.7706954904070289,
1081
+ "mrr_at_100":0.7706954904070289,
1082
+ "naucs_at_1_max":0.21266459227612405,
1083
+ "naucs_at_1_std":0.19096494070335385,
1084
+ "naucs_at_1_diff1":0.49249886565541523,
1085
+ "naucs_at_3_max":-0.03430599620876157,
1086
+ "naucs_at_3_std":0.017097041956098673,
1087
+ "naucs_at_3_diff1":-0.03264969467214677,
1088
+ "naucs_at_5_max":-0.022484350271713836,
1089
+ "naucs_at_5_std":-0.0636467385979771,
1090
+ "naucs_at_5_diff1":-0.16473803715393007,
1091
+ "naucs_at_10_max":-0.07317891510820472,
1092
+ "naucs_at_10_std":-0.04140978466752904,
1093
+ "naucs_at_10_diff1":-0.26462899584834276,
1094
+ "naucs_at_20_max":-0.0627742919035184,
1095
+ "naucs_at_20_std":0.04670746961963372,
1096
+ "naucs_at_20_diff1":-0.3704708282580158,
1097
+ "naucs_at_50_max":-0.06988684901669139,
1098
+ "naucs_at_50_std":0.005284407101443551,
1099
+ "naucs_at_50_diff1":-0.38324540988500305,
1100
+ "naucs_at_100_max":-0.11684726414295883,
1101
+ "naucs_at_100_std":0.005824353791349827,
1102
+ "naucs_at_100_diff1":-0.3791953702270732
1103
+ }
1104
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
3
+ size 11422063
tokenizer_config.json ADDED
@@ -0,0 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "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",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "max_length": null,
204
+ "model_max_length": 131072,
205
+ "pad_to_multiple_of": null,
206
+ "pad_token": "<|endoftext|>",
207
+ "pad_token_type_id": 0,
208
+ "padding_side": "left",
209
+ "processor_class": "ColQwen2_5_Processor",
210
+ "split_special_tokens": false,
211
+ "tokenizer_class": "Qwen2Tokenizer",
212
+ "unk_token": null
213
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff