Visual Document Retrieval
ColPali
Safetensors
English
vidore
vidore-experimental
QuentinJG commited on
Commit
bee760d
·
verified ·
1 Parent(s): 37d4e13

Add files using upload-large-folder tool

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
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: vidore/colqwen2.5-base
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
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:d8a0a2aa5b97160cde30d9fc26874e11f7c9dfce607fd3e2a02c91a09b17e697
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
+ }
git_hash.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 67f724577dd70727a08a96a38e7ddb05e3946050
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": "Qwen2_5_VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
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
+ "max_pixels": 12845056,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
results.json ADDED
@@ -0,0 +1,588 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "timestamp": "2025-01-30T14:08:26.760026",
4
+ "vidore_benchmark_version": "4.0.3.dev20+g2d72668"
5
+ },
6
+ "metrics": {
7
+ "arxivqa_test_subsampled": {
8
+ "ndcg_at_1": 0.83,
9
+ "ndcg_at_3": 0.87855,
10
+ "ndcg_at_5": 0.88517,
11
+ "ndcg_at_10": 0.8947,
12
+ "ndcg_at_20": 0.89981,
13
+ "ndcg_at_50": 0.90189,
14
+ "ndcg_at_100": 0.90285,
15
+ "map_at_1": 0.83,
16
+ "map_at_3": 0.86633,
17
+ "map_at_5": 0.87003,
18
+ "map_at_10": 0.87386,
19
+ "map_at_20": 0.87529,
20
+ "map_at_50": 0.87566,
21
+ "map_at_100": 0.87574,
22
+ "recall_at_1": 0.83,
23
+ "recall_at_3": 0.914,
24
+ "recall_at_5": 0.93,
25
+ "recall_at_10": 0.96,
26
+ "recall_at_20": 0.98,
27
+ "recall_at_50": 0.99,
28
+ "recall_at_100": 0.996,
29
+ "precision_at_1": 0.83,
30
+ "precision_at_3": 0.30467,
31
+ "precision_at_5": 0.186,
32
+ "precision_at_10": 0.096,
33
+ "precision_at_20": 0.049,
34
+ "precision_at_50": 0.0198,
35
+ "precision_at_100": 0.00996,
36
+ "mrr_at_1": 0.834,
37
+ "mrr_at_3": 0.8696666666666666,
38
+ "mrr_at_5": 0.8724666666666667,
39
+ "mrr_at_10": 0.8768738095238096,
40
+ "mrr_at_20": 0.8780439976689977,
41
+ "mrr_at_50": 0.8784954053717398,
42
+ "mrr_at_100": 0.8785747821152928,
43
+ "naucs_at_1_max": 0.7814883612933191,
44
+ "naucs_at_1_std": -0.014564346665118771,
45
+ "naucs_at_1_diff1": 0.9431415800777861,
46
+ "naucs_at_3_max": 0.7651293075369701,
47
+ "naucs_at_3_std": 0.13162008989642363,
48
+ "naucs_at_3_diff1": 0.876392417432091,
49
+ "naucs_at_5_max": 0.7719887955182062,
50
+ "naucs_at_5_std": 0.12731759370415013,
51
+ "naucs_at_5_diff1": 0.8762838468720809,
52
+ "naucs_at_10_max": 0.8234126984126983,
53
+ "naucs_at_10_std": 0.03160597572361713,
54
+ "naucs_at_10_diff1": 0.8921568627450972,
55
+ "naucs_at_20_max": 0.8225957049486448,
56
+ "naucs_at_20_std": -0.02110177404295123,
57
+ "naucs_at_20_diff1": 0.9084967320261399,
58
+ "naucs_at_50_max": 0.9738562091503188,
59
+ "naucs_at_50_std": 0.3997198879551785,
60
+ "naucs_at_50_diff1": 0.947712418300658,
61
+ "naucs_at_100_max": 1.0,
62
+ "naucs_at_100_std": 1.0,
63
+ "naucs_at_100_diff1": 0.9346405228758466
64
+ },
65
+ "docvqa_test_subsampled": {
66
+ "ndcg_at_1": 0.5255,
67
+ "ndcg_at_3": 0.59582,
68
+ "ndcg_at_5": 0.61852,
69
+ "ndcg_at_10": 0.6347,
70
+ "ndcg_at_20": 0.6492,
71
+ "ndcg_at_50": 0.65706,
72
+ "ndcg_at_100": 0.66361,
73
+ "map_at_1": 0.5255,
74
+ "map_at_3": 0.57871,
75
+ "map_at_5": 0.59124,
76
+ "map_at_10": 0.59815,
77
+ "map_at_20": 0.6021,
78
+ "map_at_50": 0.60333,
79
+ "map_at_100": 0.60394,
80
+ "recall_at_1": 0.5255,
81
+ "recall_at_3": 0.64523,
82
+ "recall_at_5": 0.70067,
83
+ "recall_at_10": 0.74945,
84
+ "recall_at_20": 0.8071,
85
+ "recall_at_50": 0.84701,
86
+ "recall_at_100": 0.88692,
87
+ "precision_at_1": 0.5255,
88
+ "precision_at_3": 0.21508,
89
+ "precision_at_5": 0.14013,
90
+ "precision_at_10": 0.07494,
91
+ "precision_at_20": 0.04035,
92
+ "precision_at_50": 0.01694,
93
+ "precision_at_100": 0.00887,
94
+ "mrr_at_1": 0.5254988913525499,
95
+ "mrr_at_3": 0.5798226164079823,
96
+ "mrr_at_5": 0.5909090909090909,
97
+ "mrr_at_10": 0.5981936085594622,
98
+ "mrr_at_20": 0.6018577072277826,
99
+ "mrr_at_50": 0.603184631365057,
100
+ "mrr_at_100": 0.6036950361798563,
101
+ "naucs_at_1_max": 0.3862474572443775,
102
+ "naucs_at_1_std": 0.6866980709008784,
103
+ "naucs_at_1_diff1": 0.908866111398327,
104
+ "naucs_at_3_max": 0.3232612877463118,
105
+ "naucs_at_3_std": 0.7754733885431401,
106
+ "naucs_at_3_diff1": 0.8488934990862631,
107
+ "naucs_at_5_max": 0.26561580627789727,
108
+ "naucs_at_5_std": 0.8294969802329596,
109
+ "naucs_at_5_diff1": 0.843549438877749,
110
+ "naucs_at_10_max": 0.21226897631460165,
111
+ "naucs_at_10_std": 0.9004830786766392,
112
+ "naucs_at_10_diff1": 0.8313389289681655,
113
+ "naucs_at_20_max": 0.1442628756616487,
114
+ "naucs_at_20_std": 0.9192991363569017,
115
+ "naucs_at_20_diff1": 0.8284091873092273,
116
+ "naucs_at_50_max": 0.04661475790032267,
117
+ "naucs_at_50_std": 0.9356118889205624,
118
+ "naucs_at_50_diff1": 0.8459735188892017,
119
+ "naucs_at_100_max": -0.014764226166713695,
120
+ "naucs_at_100_std": 0.9484296739649325,
121
+ "naucs_at_100_diff1": 0.853153345512516
122
+ },
123
+ "syntheticDocQA_energy_test": {
124
+ "ndcg_at_1": 0.95,
125
+ "ndcg_at_3": 0.96131,
126
+ "ndcg_at_5": 0.96131,
127
+ "ndcg_at_10": 0.96487,
128
+ "ndcg_at_20": 0.96757,
129
+ "ndcg_at_50": 0.96952,
130
+ "ndcg_at_100": 0.96952,
131
+ "map_at_1": 0.95,
132
+ "map_at_3": 0.95833,
133
+ "map_at_5": 0.95833,
134
+ "map_at_10": 0.96,
135
+ "map_at_20": 0.96083,
136
+ "map_at_50": 0.96113,
137
+ "map_at_100": 0.96113,
138
+ "recall_at_1": 0.95,
139
+ "recall_at_3": 0.97,
140
+ "recall_at_5": 0.97,
141
+ "recall_at_10": 0.98,
142
+ "recall_at_20": 0.99,
143
+ "recall_at_50": 1.0,
144
+ "recall_at_100": 1.0,
145
+ "precision_at_1": 0.95,
146
+ "precision_at_3": 0.32333,
147
+ "precision_at_5": 0.194,
148
+ "precision_at_10": 0.098,
149
+ "precision_at_20": 0.0495,
150
+ "precision_at_50": 0.02,
151
+ "precision_at_100": 0.01,
152
+ "mrr_at_1": 0.95,
153
+ "mrr_at_3": 0.9583333333333333,
154
+ "mrr_at_5": 0.9603333333333333,
155
+ "mrr_at_10": 0.9603333333333333,
156
+ "mrr_at_20": 0.9612424242424242,
157
+ "mrr_at_50": 0.9615549242424243,
158
+ "mrr_at_100": 0.9615549242424243,
159
+ "naucs_at_1_max": 0.5612511671335213,
160
+ "naucs_at_1_std": -0.8497665732959815,
161
+ "naucs_at_1_diff1": 0.9477124183006508,
162
+ "naucs_at_3_max": 0.807812013694371,
163
+ "naucs_at_3_std": -0.6484593837535022,
164
+ "naucs_at_3_diff1": 0.9564270152505466,
165
+ "naucs_at_5_max": 0.807812013694364,
166
+ "naucs_at_5_std": -0.6484593837535011,
167
+ "naucs_at_5_diff1": 0.9564270152505424,
168
+ "naucs_at_10_max": 0.9346405228758136,
169
+ "naucs_at_10_std": -0.10270774976657283,
170
+ "naucs_at_10_diff1": 0.9346405228758136,
171
+ "naucs_at_20_max": 0.8692810457516413,
172
+ "naucs_at_20_std": -0.5634920634920767,
173
+ "naucs_at_20_diff1": 1.0,
174
+ "naucs_at_50_max": null,
175
+ "naucs_at_50_std": null,
176
+ "naucs_at_50_diff1": null,
177
+ "naucs_at_100_max": null,
178
+ "naucs_at_100_std": null,
179
+ "naucs_at_100_diff1": null
180
+ },
181
+ "tatdqa_test": {
182
+ "ndcg_at_1": 0.69502,
183
+ "ndcg_at_3": 0.78919,
184
+ "ndcg_at_5": 0.80833,
185
+ "ndcg_at_10": 0.82129,
186
+ "ndcg_at_20": 0.82519,
187
+ "ndcg_at_50": 0.82963,
188
+ "ndcg_at_100": 0.83159,
189
+ "map_at_1": 0.69502,
190
+ "map_at_3": 0.76701,
191
+ "map_at_5": 0.77755,
192
+ "map_at_10": 0.78302,
193
+ "map_at_20": 0.7842,
194
+ "map_at_50": 0.78491,
195
+ "map_at_100": 0.78508,
196
+ "recall_at_1": 0.69502,
197
+ "recall_at_3": 0.85298,
198
+ "recall_at_5": 0.89976,
199
+ "recall_at_10": 0.93925,
200
+ "recall_at_20": 0.95383,
201
+ "recall_at_50": 0.97631,
202
+ "recall_at_100": 0.98846,
203
+ "precision_at_1": 0.69502,
204
+ "precision_at_3": 0.28433,
205
+ "precision_at_5": 0.17995,
206
+ "precision_at_10": 0.09392,
207
+ "precision_at_20": 0.04769,
208
+ "precision_at_50": 0.01953,
209
+ "precision_at_100": 0.00988,
210
+ "mrr_at_1": 0.6950182260024301,
211
+ "mrr_at_3": 0.7656946132037261,
212
+ "mrr_at_5": 0.7770554880518429,
213
+ "mrr_at_10": 0.7827320681208895,
214
+ "mrr_at_20": 0.783837406855329,
215
+ "mrr_at_50": 0.784510459247072,
216
+ "mrr_at_100": 0.7846961562032659,
217
+ "naucs_at_1_max": 0.2747145592665206,
218
+ "naucs_at_1_std": -0.09557716491043182,
219
+ "naucs_at_1_diff1": 0.8084384046681937,
220
+ "naucs_at_3_max": 0.3330280541363154,
221
+ "naucs_at_3_std": -0.0389562599865292,
222
+ "naucs_at_3_diff1": 0.7240601862039753,
223
+ "naucs_at_5_max": 0.352919194006459,
224
+ "naucs_at_5_std": 0.0514244344972758,
225
+ "naucs_at_5_diff1": 0.6583624352004738,
226
+ "naucs_at_10_max": 0.43229730811413347,
227
+ "naucs_at_10_std": 0.2815741957749473,
228
+ "naucs_at_10_diff1": 0.6007108794001051,
229
+ "naucs_at_20_max": 0.4241317350379727,
230
+ "naucs_at_20_std": 0.2971486230084223,
231
+ "naucs_at_20_diff1": 0.5874614197126973,
232
+ "naucs_at_50_max": 0.5140385840003181,
233
+ "naucs_at_50_std": 0.518664544400799,
234
+ "naucs_at_50_diff1": 0.5976629425860989,
235
+ "naucs_at_100_max": 0.4955447990957944,
236
+ "naucs_at_100_std": 0.5556756488737464,
237
+ "naucs_at_100_diff1": 0.6696787538618733
238
+ },
239
+ "infovqa_test_subsampled": {
240
+ "ndcg_at_1": 0.88664,
241
+ "ndcg_at_3": 0.91826,
242
+ "ndcg_at_5": 0.92479,
243
+ "ndcg_at_10": 0.93028,
244
+ "ndcg_at_20": 0.93185,
245
+ "ndcg_at_50": 0.93365,
246
+ "ndcg_at_100": 0.93435,
247
+ "map_at_1": 0.88664,
248
+ "map_at_3": 0.91093,
249
+ "map_at_5": 0.91447,
250
+ "map_at_10": 0.91689,
251
+ "map_at_20": 0.91735,
252
+ "map_at_50": 0.91756,
253
+ "map_at_100": 0.91763,
254
+ "recall_at_1": 0.88664,
255
+ "recall_at_3": 0.93927,
256
+ "recall_at_5": 0.95547,
257
+ "recall_at_10": 0.97166,
258
+ "recall_at_20": 0.97773,
259
+ "recall_at_50": 0.98785,
260
+ "recall_at_100": 0.9919,
261
+ "precision_at_1": 0.88664,
262
+ "precision_at_3": 0.31309,
263
+ "precision_at_5": 0.19109,
264
+ "precision_at_10": 0.09717,
265
+ "precision_at_20": 0.04889,
266
+ "precision_at_50": 0.01976,
267
+ "precision_at_100": 0.00992,
268
+ "mrr_at_1": 0.8846153846153846,
269
+ "mrr_at_3": 0.9092442645074225,
270
+ "mrr_at_5": 0.9127867746288799,
271
+ "mrr_at_10": 0.9150801683696421,
272
+ "mrr_at_20": 0.9155341004025214,
273
+ "mrr_at_50": 0.9157652608527469,
274
+ "mrr_at_100": 0.9158356239262059,
275
+ "naucs_at_1_max": 0.6077965938527005,
276
+ "naucs_at_1_std": -0.034859963613718514,
277
+ "naucs_at_1_diff1": 0.9382491207886892,
278
+ "naucs_at_3_max": 0.7083430308645834,
279
+ "naucs_at_3_std": 0.09173878193665044,
280
+ "naucs_at_3_diff1": 0.941058293792039,
281
+ "naucs_at_5_max": 0.828261285914772,
282
+ "naucs_at_5_std": 0.25360809635439513,
283
+ "naucs_at_5_diff1": 0.9374342352707031,
284
+ "naucs_at_10_max": 0.8969865162710334,
285
+ "naucs_at_10_std": 0.5367916133086486,
286
+ "naucs_at_10_diff1": 0.9521757785748344,
287
+ "naucs_at_20_max": 0.927259949634811,
288
+ "naucs_at_20_std": 0.6312197158498455,
289
+ "naucs_at_20_diff1": 0.9643814216187027,
290
+ "naucs_at_50_max": 0.9129323639568211,
291
+ "naucs_at_50_std": 0.5625809313845725,
292
+ "naucs_at_50_diff1": 0.9564661819783937,
293
+ "naucs_at_100_max": 0.9346992729676393,
294
+ "naucs_at_100_std": 0.7480140525249407,
295
+ "naucs_at_100_diff1": 0.9673496364838197
296
+ },
297
+ "syntheticDocQA_healthcare_industry_test": {
298
+ "ndcg_at_1": 0.97,
299
+ "ndcg_at_3": 0.98762,
300
+ "ndcg_at_5": 0.98762,
301
+ "ndcg_at_10": 0.98762,
302
+ "ndcg_at_20": 0.98762,
303
+ "ndcg_at_50": 0.98762,
304
+ "ndcg_at_100": 0.98762,
305
+ "map_at_1": 0.97,
306
+ "map_at_3": 0.98333,
307
+ "map_at_5": 0.98333,
308
+ "map_at_10": 0.98333,
309
+ "map_at_20": 0.98333,
310
+ "map_at_50": 0.98333,
311
+ "map_at_100": 0.98333,
312
+ "recall_at_1": 0.97,
313
+ "recall_at_3": 1.0,
314
+ "recall_at_5": 1.0,
315
+ "recall_at_10": 1.0,
316
+ "recall_at_20": 1.0,
317
+ "recall_at_50": 1.0,
318
+ "recall_at_100": 1.0,
319
+ "precision_at_1": 0.97,
320
+ "precision_at_3": 0.33333,
321
+ "precision_at_5": 0.2,
322
+ "precision_at_10": 0.1,
323
+ "precision_at_20": 0.05,
324
+ "precision_at_50": 0.02,
325
+ "precision_at_100": 0.01,
326
+ "mrr_at_1": 0.97,
327
+ "mrr_at_3": 0.9833333333333333,
328
+ "mrr_at_5": 0.9833333333333333,
329
+ "mrr_at_10": 0.9833333333333333,
330
+ "mrr_at_20": 0.9833333333333333,
331
+ "mrr_at_50": 0.9833333333333333,
332
+ "mrr_at_100": 0.9833333333333333,
333
+ "naucs_at_1_max": 0.8202614379084989,
334
+ "naucs_at_1_std": -0.2198879551820713,
335
+ "naucs_at_1_diff1": 0.9564270152505465,
336
+ "naucs_at_3_max": 1.0,
337
+ "naucs_at_3_std": 1.0,
338
+ "naucs_at_3_diff1": 1.0,
339
+ "naucs_at_5_max": 1.0,
340
+ "naucs_at_5_std": 1.0,
341
+ "naucs_at_5_diff1": 1.0,
342
+ "naucs_at_10_max": 1.0,
343
+ "naucs_at_10_std": 1.0,
344
+ "naucs_at_10_diff1": 1.0,
345
+ "naucs_at_20_max": 1.0,
346
+ "naucs_at_20_std": 1.0,
347
+ "naucs_at_20_diff1": 1.0,
348
+ "naucs_at_50_max": null,
349
+ "naucs_at_50_std": null,
350
+ "naucs_at_50_diff1": null,
351
+ "naucs_at_100_max": null,
352
+ "naucs_at_100_std": null,
353
+ "naucs_at_100_diff1": null
354
+ },
355
+ "tabfquad_test_subsampled": {
356
+ "ndcg_at_1": 0.83571,
357
+ "ndcg_at_3": 0.88699,
358
+ "ndcg_at_5": 0.89851,
359
+ "ndcg_at_10": 0.90549,
360
+ "ndcg_at_20": 0.91018,
361
+ "ndcg_at_50": 0.9125,
362
+ "ndcg_at_100": 0.9125,
363
+ "map_at_1": 0.83571,
364
+ "map_at_3": 0.875,
365
+ "map_at_5": 0.88125,
366
+ "map_at_10": 0.88416,
367
+ "map_at_20": 0.88553,
368
+ "map_at_50": 0.88598,
369
+ "map_at_100": 0.88598,
370
+ "recall_at_1": 0.83571,
371
+ "recall_at_3": 0.92143,
372
+ "recall_at_5": 0.95,
373
+ "recall_at_10": 0.97143,
374
+ "recall_at_20": 0.98929,
375
+ "recall_at_50": 1.0,
376
+ "recall_at_100": 1.0,
377
+ "precision_at_1": 0.83571,
378
+ "precision_at_3": 0.30714,
379
+ "precision_at_5": 0.19,
380
+ "precision_at_10": 0.09714,
381
+ "precision_at_20": 0.04946,
382
+ "precision_at_50": 0.02,
383
+ "precision_at_100": 0.01,
384
+ "mrr_at_1": 0.8392857142857143,
385
+ "mrr_at_3": 0.8767857142857143,
386
+ "mrr_at_5": 0.8830357142857143,
387
+ "mrr_at_10": 0.8858517573696145,
388
+ "mrr_at_20": 0.8872690305726021,
389
+ "mrr_at_50": 0.8877252707609851,
390
+ "mrr_at_100": 0.8877252707609851,
391
+ "naucs_at_1_max": 0.4880524536858767,
392
+ "naucs_at_1_std": 0.1966050571171859,
393
+ "naucs_at_1_diff1": 0.9065802421597565,
394
+ "naucs_at_3_max": 0.5683515830574649,
395
+ "naucs_at_3_std": 0.33952975129445734,
396
+ "naucs_at_3_diff1": 0.8935786435786452,
397
+ "naucs_at_5_max": 0.7507669734560504,
398
+ "naucs_at_5_std": 0.5118714152327615,
399
+ "naucs_at_5_diff1": 0.9109643857543043,
400
+ "naucs_at_10_max": 0.8150093370681609,
401
+ "naucs_at_10_std": 0.5556722689075682,
402
+ "naucs_at_10_diff1": 0.934640522875815,
403
+ "naucs_at_20_max": 0.9128540305011011,
404
+ "naucs_at_20_std": 0.807812013694365,
405
+ "naucs_at_20_diff1": 0.9564270152505505,
406
+ "naucs_at_50_max": 1.0,
407
+ "naucs_at_50_std": 1.0,
408
+ "naucs_at_50_diff1": 1.0,
409
+ "naucs_at_100_max": 1.0,
410
+ "naucs_at_100_std": 1.0,
411
+ "naucs_at_100_diff1": 1.0
412
+ },
413
+ "syntheticDocQA_government_reports_test": {
414
+ "ndcg_at_1": 0.91,
415
+ "ndcg_at_3": 0.94393,
416
+ "ndcg_at_5": 0.95254,
417
+ "ndcg_at_10": 0.9561,
418
+ "ndcg_at_20": 0.9561,
419
+ "ndcg_at_50": 0.9561,
420
+ "ndcg_at_100": 0.9561,
421
+ "map_at_1": 0.91,
422
+ "map_at_3": 0.935,
423
+ "map_at_5": 0.94,
424
+ "map_at_10": 0.94167,
425
+ "map_at_20": 0.94167,
426
+ "map_at_50": 0.94167,
427
+ "map_at_100": 0.94167,
428
+ "recall_at_1": 0.91,
429
+ "recall_at_3": 0.97,
430
+ "recall_at_5": 0.99,
431
+ "recall_at_10": 1.0,
432
+ "recall_at_20": 1.0,
433
+ "recall_at_50": 1.0,
434
+ "recall_at_100": 1.0,
435
+ "precision_at_1": 0.91,
436
+ "precision_at_3": 0.32333,
437
+ "precision_at_5": 0.198,
438
+ "precision_at_10": 0.1,
439
+ "precision_at_20": 0.05,
440
+ "precision_at_50": 0.02,
441
+ "precision_at_100": 0.01,
442
+ "mrr_at_1": 0.91,
443
+ "mrr_at_3": 0.9383333333333332,
444
+ "mrr_at_5": 0.9428333333333333,
445
+ "mrr_at_10": 0.9428333333333333,
446
+ "mrr_at_20": 0.9428333333333333,
447
+ "mrr_at_50": 0.9428333333333333,
448
+ "mrr_at_100": 0.9428333333333333,
449
+ "naucs_at_1_max": 0.8246706089843343,
450
+ "naucs_at_1_std": 0.4518103537711367,
451
+ "naucs_at_1_diff1": 0.9564270152505436,
452
+ "naucs_at_3_max": 0.7027699968876487,
453
+ "naucs_at_3_std": 0.460939931528168,
454
+ "naucs_at_3_diff1": 0.9564270152505466,
455
+ "naucs_at_5_max": 0.5541549953314738,
456
+ "naucs_at_5_std": -0.1713352007469681,
457
+ "naucs_at_5_diff1": 1.0,
458
+ "naucs_at_10_max": 1.0,
459
+ "naucs_at_10_std": 1.0,
460
+ "naucs_at_10_diff1": 1.0,
461
+ "naucs_at_20_max": 1.0,
462
+ "naucs_at_20_std": 1.0,
463
+ "naucs_at_20_diff1": 1.0,
464
+ "naucs_at_50_max": null,
465
+ "naucs_at_50_std": null,
466
+ "naucs_at_50_diff1": null,
467
+ "naucs_at_100_max": null,
468
+ "naucs_at_100_std": null,
469
+ "naucs_at_100_diff1": null
470
+ },
471
+ "shiftproject_test": {
472
+ "ndcg_at_1": 0.73,
473
+ "ndcg_at_3": 0.85095,
474
+ "ndcg_at_5": 0.85526,
475
+ "ndcg_at_10": 0.86174,
476
+ "ndcg_at_20": 0.86703,
477
+ "ndcg_at_50": 0.87134,
478
+ "ndcg_at_100": 0.87134,
479
+ "map_at_1": 0.73,
480
+ "map_at_3": 0.82333,
481
+ "map_at_5": 0.82583,
482
+ "map_at_10": 0.82851,
483
+ "map_at_20": 0.83009,
484
+ "map_at_50": 0.83092,
485
+ "map_at_100": 0.83092,
486
+ "recall_at_1": 0.73,
487
+ "recall_at_3": 0.93,
488
+ "recall_at_5": 0.94,
489
+ "recall_at_10": 0.96,
490
+ "recall_at_20": 0.98,
491
+ "recall_at_50": 1.0,
492
+ "recall_at_100": 1.0,
493
+ "precision_at_1": 0.73,
494
+ "precision_at_3": 0.31,
495
+ "precision_at_5": 0.188,
496
+ "precision_at_10": 0.096,
497
+ "precision_at_20": 0.049,
498
+ "precision_at_50": 0.02,
499
+ "precision_at_100": 0.01,
500
+ "mrr_at_1": 0.75,
501
+ "mrr_at_3": 0.8316666666666667,
502
+ "mrr_at_5": 0.8341666666666667,
503
+ "mrr_at_10": 0.8380238095238096,
504
+ "mrr_at_20": 0.8386904761904762,
505
+ "mrr_at_50": 0.8395600414078674,
506
+ "mrr_at_100": 0.8395600414078674,
507
+ "naucs_at_1_max": -0.0662092826672433,
508
+ "naucs_at_1_std": -0.3356071477717276,
509
+ "naucs_at_1_diff1": 0.7686999941024986,
510
+ "naucs_at_3_max": -0.05822328931572497,
511
+ "naucs_at_3_std": -0.2665732959850601,
512
+ "naucs_at_3_diff1": 0.7789782579698524,
513
+ "naucs_at_5_max": 0.22206660441954526,
514
+ "naucs_at_5_std": -0.33146591970121353,
515
+ "naucs_at_5_diff1": 0.8883442265795238,
516
+ "naucs_at_10_max": 0.05240429505135564,
517
+ "naucs_at_10_std": -0.4458450046685252,
518
+ "naucs_at_10_diff1": 0.8651960784313721,
519
+ "naucs_at_20_max": -0.5088702147525547,
520
+ "naucs_at_20_std": -0.5929038281979383,
521
+ "naucs_at_20_diff1": 0.9346405228758136,
522
+ "naucs_at_50_max": null,
523
+ "naucs_at_50_std": null,
524
+ "naucs_at_50_diff1": null,
525
+ "naucs_at_100_max": null,
526
+ "naucs_at_100_std": null,
527
+ "naucs_at_100_diff1": null
528
+ },
529
+ "syntheticDocQA_artificial_intelligence_test": {
530
+ "ndcg_at_1": 0.98,
531
+ "ndcg_at_3": 0.99262,
532
+ "ndcg_at_5": 0.99262,
533
+ "ndcg_at_10": 0.99262,
534
+ "ndcg_at_20": 0.99262,
535
+ "ndcg_at_50": 0.99262,
536
+ "ndcg_at_100": 0.99262,
537
+ "map_at_1": 0.98,
538
+ "map_at_3": 0.99,
539
+ "map_at_5": 0.99,
540
+ "map_at_10": 0.99,
541
+ "map_at_20": 0.99,
542
+ "map_at_50": 0.99,
543
+ "map_at_100": 0.99,
544
+ "recall_at_1": 0.98,
545
+ "recall_at_3": 1.0,
546
+ "recall_at_5": 1.0,
547
+ "recall_at_10": 1.0,
548
+ "recall_at_20": 1.0,
549
+ "recall_at_50": 1.0,
550
+ "recall_at_100": 1.0,
551
+ "precision_at_1": 0.98,
552
+ "precision_at_3": 0.33333,
553
+ "precision_at_5": 0.2,
554
+ "precision_at_10": 0.1,
555
+ "precision_at_20": 0.05,
556
+ "precision_at_50": 0.02,
557
+ "precision_at_100": 0.01,
558
+ "mrr_at_1": 0.98,
559
+ "mrr_at_3": 0.99,
560
+ "mrr_at_5": 0.99,
561
+ "mrr_at_10": 0.99,
562
+ "mrr_at_20": 0.99,
563
+ "mrr_at_50": 0.99,
564
+ "mrr_at_100": 0.99,
565
+ "naucs_at_1_max": 0.3489729225023353,
566
+ "naucs_at_1_std": -0.2987861811391249,
567
+ "naucs_at_1_diff1": 1.0,
568
+ "naucs_at_3_max": 1.0,
569
+ "naucs_at_3_std": 1.0,
570
+ "naucs_at_3_diff1": 1.0,
571
+ "naucs_at_5_max": 1.0,
572
+ "naucs_at_5_std": 1.0,
573
+ "naucs_at_5_diff1": 1.0,
574
+ "naucs_at_10_max": 1.0,
575
+ "naucs_at_10_std": 1.0,
576
+ "naucs_at_10_diff1": 1.0,
577
+ "naucs_at_20_max": 1.0,
578
+ "naucs_at_20_std": 1.0,
579
+ "naucs_at_20_diff1": 1.0,
580
+ "naucs_at_50_max": null,
581
+ "naucs_at_50_std": null,
582
+ "naucs_at_50_diff1": null,
583
+ "naucs_at_100_max": null,
584
+ "naucs_at_100_std": null,
585
+ "naucs_at_100_diff1": null
586
+ }
587
+ }
588
+ }
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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "processor_class": "ColQwen2_5_Processor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
training_config.yml ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config:
2
+ (): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
3
+ output_dir: !path ../../../models/colqwen2_5_train
4
+ processor:
5
+ (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
6
+ class_to_instanciate: !ext colpali_engine.models.ColQwen2_5_Processor
7
+ pretrained_model_name_or_path: "./models/ColQwen2.5-VL-3B-Instruct" # "./models/paligemma-3b-mix-448"
8
+ # num_image_tokens: 2048
9
+ # max_length: 50
10
+
11
+ model:
12
+ (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
13
+ class_to_instanciate: !ext colpali_engine.models.ColQwen2_5
14
+ pretrained_model_name_or_path: "./models/ColQwen2.5-VL-3B-Instruct"
15
+ torch_dtype: !ext torch.bfloat16
16
+ use_cache: false
17
+ attn_implementation: "flash_attention_2"
18
+ # device_map: "auto"
19
+ # quantization_config:
20
+ # (): transformers.BitsAndBytesConfig
21
+ # load_in_4bit: true
22
+ # bnb_4bit_quant_type: "nf4"
23
+ # bnb_4bit_compute_dtype: "bfloat16"
24
+ # bnb_4bit_use_double_quant: true
25
+
26
+ dataset_loading_func: !ext colpali_engine.utils.dataset_transformation.load_train_set
27
+ eval_dataset_loader: !import ../data/test_data.yaml
28
+
29
+ # max_length: 50
30
+ run_eval: true
31
+ loss_func:
32
+ (): colpali_engine.loss.late_interaction_losses.ColbertPairwiseCELoss
33
+ tr_args:
34
+ (): transformers.training_args.TrainingArguments
35
+ output_dir: null
36
+ overwrite_output_dir: true
37
+ num_train_epochs: 3
38
+ per_device_train_batch_size: 32
39
+ gradient_checkpointing: true
40
+ gradient_checkpointing_kwargs: { "use_reentrant": false }
41
+ # gradient_checkpointing: true
42
+ # 6 x 8 gpus = 48 batch size
43
+ # gradient_accumulation_steps: 4
44
+ per_device_eval_batch_size: 16
45
+ eval_strategy: "steps"
46
+ dataloader_num_workers: 8
47
+ # bf16: true
48
+ save_steps: 500
49
+ logging_steps: 10
50
+ eval_steps: 100
51
+ warmup_steps: 500
52
+ learning_rate: 1e-4
53
+ save_total_limit: 1
54
+ # resume_from_checkpoint: true
55
+ # optim: "paged_adamw_8bit"
56
+ # wandb logging
57
+ # wandb_project: "colqwen2"
58
+ # run_name: "colqwen2-ba32-nolora"
59
+ report_to: "wandb"
60
+
61
+
62
+ peft_config:
63
+ (): peft.LoraConfig
64
+ r: 32
65
+ lora_alpha: 32
66
+ lora_dropout: 0.1
67
+ init_lora_weights: "gaussian"
68
+ bias: "none"
69
+ task_type: "FEATURE_EXTRACTION"
70
+ target_modules: '(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
71
+ # target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
72
+
vocab.json ADDED
The diff for this file is too large to render. See raw diff