manu commited on
Commit
bbfb67d
1 Parent(s): 6d7a9ff

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: vidore/colqwen2-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 0.11.1
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "vidore/colqwen2-base",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": "gaussian",
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
23
+ "task_type": "FEATURE_EXTRACTION",
24
+ "use_dora": false,
25
+ "use_rslora": false
26
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f197f2601d0136d0af935a8da98b4409bc7ed82f33d5527a870a5c21a0abe0
3
+ size 74018232
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
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
+ 3ec85f462475d4564d0926a885fc5fe1b95e606d
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": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "ColQwen2Processor",
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 @@
 
 
1
+ {"validation_set": {"ndcg_at_1": 0.816, "ndcg_at_3": 0.87743, "ndcg_at_5": 0.88801, "ndcg_at_10": 0.89049, "ndcg_at_20": 0.89308, "ndcg_at_100": 0.8984, "ndcg_at_1000": 0.89954, "map_at_1": 0.816, "map_at_3": 0.86267, "map_at_5": 0.86847, "map_at_10": 0.86942, "map_at_20": 0.87018, "map_at_100": 0.87095, "map_at_1000": 0.87101, "recall_at_1": 0.816, "recall_at_3": 0.92, "recall_at_5": 0.946, "recall_at_10": 0.954, "recall_at_20": 0.964, "recall_at_100": 0.992, "recall_at_1000": 1.0, "precision_at_1": 0.816, "precision_at_3": 0.30667, "precision_at_5": 0.1892, "precision_at_10": 0.0954, "precision_at_20": 0.0482, "precision_at_100": 0.00992, "precision_at_1000": 0.001, "mrr_at_1": 0.82, "mrr_at_3": 0.8629999999999998, "mrr_at_5": 0.8703999999999998, "mrr_at_10": 0.8713301587301585, "mrr_at_20": 0.8723493506493503, "mrr_at_100": 0.8731067876052313, "mrr_at_1000": 0.8731343731583642, "naucs_at_1_max": 0.4089927902257919, "naucs_at_1_std": -0.3392695246729696, "naucs_at_1_diff1": 0.9499201312437934, "naucs_at_3_max": 0.5994747899159686, "naucs_at_3_std": -0.13678804855275456, "naucs_at_3_diff1": 0.9297385620915034, "naucs_at_5_max": 0.6925338036449152, "naucs_at_5_std": 0.06575716706435682, "naucs_at_5_diff1": 0.9552166545630597, "naucs_at_10_max": 0.7244955953395846, "naucs_at_10_std": 0.18962367555717077, "naucs_at_10_diff1": 0.9595055413469742, "naucs_at_20_max": 0.6799979250959618, "naucs_at_20_std": 0.15966386554621653, "naucs_at_20_diff1": 0.9700435729847436, "naucs_at_100_max": 0.5180905695611601, "naucs_at_100_std": 0.23342670401492077, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_energy": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.94786, "ndcg_at_5": 0.94786, "ndcg_at_10": 0.95101, "ndcg_at_20": 0.9538, "ndcg_at_100": 0.95601, "ndcg_at_1000": 0.95601, "map_at_1": 0.91, "map_at_3": 0.94, "map_at_5": 0.94, "map_at_10": 0.94125, "map_at_20": 0.94216, "map_at_100": 0.94261, "map_at_1000": 0.94261, "recall_at_1": 0.91, "recall_at_3": 0.97, "recall_at_5": 0.97, "recall_at_10": 0.98, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.91, "precision_at_3": 0.32333, "precision_at_5": 0.194, "precision_at_10": 0.098, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.94, "mrr_at_3": 0.955, "mrr_at_5": 0.955, "mrr_at_10": 0.9564285714285714, "mrr_at_20": 0.9573376623376624, "mrr_at_100": 0.9577922077922078, "mrr_at_1000": 0.9577922077922078, "naucs_at_1_max": 0.2695300342359169, "naucs_at_1_std": -0.6963896669779026, "naucs_at_1_diff1": 0.9854756717501807, "naucs_at_3_max": 0.5714285714285686, "naucs_at_3_std": -1.21708683473389, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 0.5714285714285722, "naucs_at_5_std": -1.2170868347338937, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 0.7957516339869297, "naucs_at_10_std": -0.9556489262371616, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 0.7222222222222276, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.96655, "ndcg_at_5": 0.96655, "ndcg_at_10": 0.96655, "ndcg_at_20": 0.96655, "ndcg_at_100": 0.96655, "ndcg_at_1000": 0.96655, "map_at_1": 0.92, "map_at_3": 0.955, "map_at_5": 0.955, "map_at_10": 0.955, "map_at_20": 0.955, "map_at_100": 0.955, "map_at_1000": 0.955, "recall_at_1": 0.92, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.94, "mrr_at_3": 0.965, "mrr_at_5": 0.965, "mrr_at_10": 0.965, "mrr_at_20": 0.965, "mrr_at_100": 0.965, "mrr_at_1000": 0.965, "naucs_at_1_max": 0.7619047619047616, "naucs_at_1_std": -0.1527777777777763, "naucs_at_1_diff1": 0.9673202614379083, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.98, "ndcg_at_3": 0.98631, "ndcg_at_5": 0.99062, "ndcg_at_10": 0.99062, "ndcg_at_20": 0.99062, "ndcg_at_100": 0.99062, "ndcg_at_1000": 0.99062, "map_at_1": 0.98, "map_at_3": 0.985, "map_at_5": 0.9875, "map_at_10": 0.9875, "map_at_20": 0.9875, "map_at_100": 0.9875, "map_at_1000": 0.9875, "recall_at_1": 0.98, "recall_at_3": 0.99, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.98, "precision_at_3": 0.33, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.98, "mrr_at_3": 0.985, "mrr_at_5": 0.9875, "mrr_at_10": 0.9875, "mrr_at_20": 0.9875, "mrr_at_100": 0.9875, "mrr_at_1000": 0.9875, "naucs_at_1_max": 0.3489729225023353, "naucs_at_1_std": -0.808590102707748, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 0.8692810457516356, "naucs_at_3_std": 0.12278244631183229, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.85, "ndcg_at_3": 0.92309, "ndcg_at_5": 0.93171, "ndcg_at_10": 0.93472, "ndcg_at_20": 0.93472, "ndcg_at_100": 0.93472, "ndcg_at_1000": 0.93472, "map_at_1": 0.85, "map_at_3": 0.90667, "map_at_5": 0.91167, "map_at_10": 0.91278, "map_at_20": 0.91278, "map_at_100": 0.91278, "map_at_1000": 0.91278, "recall_at_1": 0.85, "recall_at_3": 0.97, "recall_at_5": 0.99, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.85, "precision_at_3": 0.32333, "precision_at_5": 0.198, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.86, "mrr_at_3": 0.9116666666666666, "mrr_at_5": 0.9166666666666665, "mrr_at_10": 0.9179166666666666, "mrr_at_20": 0.9179166666666666, "mrr_at_100": 0.9179166666666666, "mrr_at_1000": 0.9179166666666666, "naucs_at_1_max": 0.4882525219655072, "naucs_at_1_std": 0.2755938821998056, "naucs_at_1_diff1": 0.8752033843150019, "naucs_at_3_max": 0.8513849984438244, "naucs_at_3_std": 0.2376283846872095, "naucs_at_3_diff1": 0.9074074074074082, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.5541549953314738, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "infovqa_subsampled": {"ndcg_at_1": 0.856, "ndcg_at_3": 0.88802, "ndcg_at_5": 0.89964, "ndcg_at_10": 0.90561, "ndcg_at_20": 0.91178, "ndcg_at_100": 0.91336, "ndcg_at_1000": 0.91519, "map_at_1": 0.856, "map_at_3": 0.881, "map_at_5": 0.8875, "map_at_10": 0.89005, "map_at_20": 0.8918, "map_at_100": 0.89206, "map_at_1000": 0.89213, "recall_at_1": 0.856, "recall_at_3": 0.908, "recall_at_5": 0.936, "recall_at_10": 0.954, "recall_at_20": 0.978, "recall_at_100": 0.986, "recall_at_1000": 1.0, "precision_at_1": 0.856, "precision_at_3": 0.30267, "precision_at_5": 0.1872, "precision_at_10": 0.0954, "precision_at_20": 0.0489, "precision_at_100": 0.00986, "precision_at_1000": 0.001, "mrr_at_1": 0.86, "mrr_at_3": 0.8839999999999999, "mrr_at_5": 0.8895999999999998, "mrr_at_10": 0.8919190476190474, "mrr_at_20": 0.893826762736747, "mrr_at_100": 0.8940837133167153, "mrr_at_1000": 0.8941572107843205, "naucs_at_1_max": 0.6396625783444994, "naucs_at_1_std": -0.11759779554787107, "naucs_at_1_diff1": 0.9412753944240329, "naucs_at_3_max": 0.5607518369666695, "naucs_at_3_std": -0.23359923679616587, "naucs_at_3_diff1": 0.8989668331100549, "naucs_at_5_max": 0.7544496965452863, "naucs_at_5_std": -0.03478057889822458, "naucs_at_5_diff1": 0.9227503501400529, "naucs_at_10_max": 0.7531157390492416, "naucs_at_10_std": -0.19932610725450334, "naucs_at_10_diff1": 0.9488491048593367, "naucs_at_20_max": 0.9163907987437411, "naucs_at_20_std": 0.24034462269756168, "naucs_at_20_diff1": 0.9524658348187754, "naucs_at_100_max": 0.9603174603174626, "naucs_at_100_std": 0.28097905828998787, "naucs_at_100_diff1": 0.9626517273576126, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.462, "ndcg_at_3": 0.52421, "ndcg_at_5": 0.55269, "ndcg_at_10": 0.58165, "ndcg_at_20": 0.59442, "ndcg_at_100": 0.61615, "ndcg_at_1000": 0.62947, "map_at_1": 0.462, "map_at_3": 0.50967, "map_at_5": 0.52527, "map_at_10": 0.5375, "map_at_20": 0.54108, "map_at_100": 0.54388, "map_at_1000": 0.54434, "recall_at_1": 0.462, "recall_at_3": 0.566, "recall_at_5": 0.636, "recall_at_10": 0.724, "recall_at_20": 0.774, "recall_at_100": 0.894, "recall_at_1000": 1.0, "precision_at_1": 0.462, "precision_at_3": 0.18867, "precision_at_5": 0.1272, "precision_at_10": 0.0724, "precision_at_20": 0.0387, "precision_at_100": 0.00894, "precision_at_1000": 0.001, "mrr_at_1": 0.464, "mrr_at_3": 0.5140000000000001, "mrr_at_5": 0.5276, "mrr_at_10": 0.5392595238095239, "mrr_at_20": 0.5427890347354745, "mrr_at_100": 0.5456342789886727, "mrr_at_1000": 0.5461156386952566, "naucs_at_1_max": 0.6458196908851354, "naucs_at_1_std": 0.20323368757675922, "naucs_at_1_diff1": 0.8721936004754803, "naucs_at_3_max": 0.6349820968797422, "naucs_at_3_std": 0.26161988232234823, "naucs_at_3_diff1": 0.7944184557880087, "naucs_at_5_max": 0.6085398087052426, "naucs_at_5_std": 0.26688090665348296, "naucs_at_5_diff1": 0.7506481076524244, "naucs_at_10_max": 0.555114948298363, "naucs_at_10_std": 0.42525464696933346, "naucs_at_10_diff1": 0.7213517332983245, "naucs_at_20_max": 0.5278038772462562, "naucs_at_20_std": 0.5622415585240862, "naucs_at_20_diff1": 0.6966560907081347, "naucs_at_100_max": 0.557859893864365, "naucs_at_100_std": 0.9139733418525807, "naucs_at_100_diff1": 0.6317288749267865, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "arxivqa_subsampled": {"ndcg_at_1": 0.802, "ndcg_at_3": 0.85338, "ndcg_at_5": 0.86732, "ndcg_at_10": 0.87428, "ndcg_at_20": 0.88107, "ndcg_at_100": 0.88546, "ndcg_at_1000": 0.88657, "map_at_1": 0.802, "map_at_3": 0.84133, "map_at_5": 0.84903, "map_at_10": 0.85181, "map_at_20": 0.85379, "map_at_100": 0.8545, "map_at_1000": 0.85456, "recall_at_1": 0.802, "recall_at_3": 0.888, "recall_at_5": 0.922, "recall_at_10": 0.944, "recall_at_20": 0.97, "recall_at_100": 0.992, "recall_at_1000": 1.0, "precision_at_1": 0.802, "precision_at_3": 0.296, "precision_at_5": 0.1844, "precision_at_10": 0.0944, "precision_at_20": 0.0485, "precision_at_100": 0.00992, "precision_at_1000": 0.001, "mrr_at_1": 0.798, "mrr_at_3": 0.8393333333333333, "mrr_at_5": 0.8470333333333331, "mrr_at_10": 0.8496023809523807, "mrr_at_20": 0.8517748418248414, "mrr_at_100": 0.8525011699855726, "mrr_at_1000": 0.8525560625613932, "naucs_at_1_max": 0.7609787332735034, "naucs_at_1_std": -0.04982403775373434, "naucs_at_1_diff1": 0.9467323457935447, "naucs_at_3_max": 0.810834347943723, "naucs_at_3_std": -0.07579985119047568, "naucs_at_3_diff1": 0.9171401515151517, "naucs_at_5_max": 0.7709665062606241, "naucs_at_5_std": -0.1451076156958529, "naucs_at_5_diff1": 0.9040556393497581, "naucs_at_10_max": 0.8141923436041086, "naucs_at_10_std": 0.03956582633053216, "naucs_at_10_diff1": 0.9042950513538771, "naucs_at_20_max": 0.7773109243697499, "naucs_at_20_std": 0.03131030189853261, "naucs_at_20_diff1": 0.8921568627450983, "naucs_at_100_max": 0.9346405228758211, "naucs_at_100_std": 0.21288515406164388, "naucs_at_100_diff1": 0.8978758169934562, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.82143, "ndcg_at_3": 0.88078, "ndcg_at_5": 0.88662, "ndcg_at_10": 0.8959, "ndcg_at_20": 0.90245, "ndcg_at_100": 0.90455, "ndcg_at_1000": 0.90455, "map_at_1": 0.82143, "map_at_3": 0.86667, "map_at_5": 0.86988, "map_at_10": 0.87373, "map_at_20": 0.87564, "map_at_100": 0.87596, "map_at_1000": 0.87596, "recall_at_1": 0.82143, "recall_at_3": 0.92143, "recall_at_5": 0.93571, "recall_at_10": 0.96429, "recall_at_20": 0.98929, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.82143, "precision_at_3": 0.30714, "precision_at_5": 0.18714, "precision_at_10": 0.09643, "precision_at_20": 0.04946, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.825, "mrr_at_3": 0.867857142857143, "mrr_at_5": 0.8712500000000002, "mrr_at_10": 0.8749943310657597, "mrr_at_20": 0.8769510053438626, "mrr_at_100": 0.877276262150675, "mrr_at_1000": 0.877276262150675, "naucs_at_1_max": 0.42563899346146206, "naucs_at_1_std": 0.1471765405191198, "naucs_at_1_diff1": 0.8586387953239548, "naucs_at_3_max": 0.5611365758424587, "naucs_at_3_std": 0.3328664799253024, "naucs_at_3_diff1": 0.8272642390289456, "naucs_at_5_max": 0.514705882352943, "naucs_at_5_std": 0.30713766988277114, "naucs_at_5_diff1": 0.7961406784936206, "naucs_at_10_max": 0.6987394957983158, "naucs_at_10_std": 0.5981325863678804, "naucs_at_10_diff1": 0.7941176470588184, "naucs_at_20_max": 0.5659819483349039, "naucs_at_20_std": 0.38624338624340593, "naucs_at_20_diff1": 0.7222222222222332, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.63981, "ndcg_at_3": 0.74917, "ndcg_at_5": 0.7759, "ndcg_at_10": 0.79135, "ndcg_at_20": 0.79694, "ndcg_at_100": 0.8024, "ndcg_at_1000": 0.80405, "map_at_1": 0.63981, "map_at_3": 0.72269, "map_at_5": 0.73766, "map_at_10": 0.74409, "map_at_20": 0.74569, "map_at_100": 0.74649, "map_at_1000": 0.74657, "recall_at_1": 0.63981, "recall_at_3": 0.82562, "recall_at_5": 0.88996, "recall_at_10": 0.93746, "recall_at_20": 0.95911, "recall_at_100": 0.98797, "recall_at_1000": 1.0, "precision_at_1": 0.63981, "precision_at_3": 0.27521, "precision_at_5": 0.17799, "precision_at_10": 0.09375, "precision_at_20": 0.04796, "precision_at_100": 0.00988, "precision_at_1000": 0.001, "mrr_at_1": 0.6361996392062538, "mrr_at_3": 0.7217879334535983, "mrr_at_5": 0.7364902786129491, "mrr_at_10": 0.7432783075146278, "mrr_at_20": 0.7447440403539413, "mrr_at_100": 0.7455222233062115, "mrr_at_1000": 0.7456073710266525, "naucs_at_1_max": 0.1755436734128544, "naucs_at_1_std": -0.3413375494454732, "naucs_at_1_diff1": 0.8028659791349476, "naucs_at_3_max": 0.22498779700389868, "naucs_at_3_std": -0.3217234939830549, "naucs_at_3_diff1": 0.709972936200294, "naucs_at_5_max": 0.30088635417517934, "naucs_at_5_std": -0.18095101115377482, "naucs_at_5_diff1": 0.6729946219402011, "naucs_at_10_max": 0.45528821068686837, "naucs_at_10_std": 0.111949278381562, "naucs_at_10_diff1": 0.5970873099232054, "naucs_at_20_max": 0.5130688154968079, "naucs_at_20_std": 0.1996874580648595, "naucs_at_20_diff1": 0.5824718780309613, "naucs_at_100_max": 0.6356023548124133, "naucs_at_100_std": 0.6258417323163146, "naucs_at_100_diff1": 0.5270310843892404, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.72, "ndcg_at_3": 0.85988, "ndcg_at_5": 0.85988, "ndcg_at_10": 0.86948, "ndcg_at_20": 0.87204, "ndcg_at_100": 0.87396, "ndcg_at_1000": 0.87396, "map_at_1": 0.72, "map_at_3": 0.82833, "map_at_5": 0.82833, "map_at_10": 0.83225, "map_at_20": 0.83296, "map_at_100": 0.83324, "map_at_1000": 0.83324, "recall_at_1": 0.72, "recall_at_3": 0.95, "recall_at_5": 0.95, "recall_at_10": 0.98, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.72, "precision_at_3": 0.31667, "precision_at_5": 0.19, "precision_at_10": 0.098, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.75, "mrr_at_3": 0.845, "mrr_at_5": 0.845, "mrr_at_10": 0.849095238095238, "mrr_at_20": 0.8498095238095238, "mrr_at_100": 0.850095238095238, "mrr_at_1000": 0.850095238095238, "naucs_at_1_max": -0.0836195054945053, "naucs_at_1_std": -0.565399877899878, "naucs_at_1_diff1": 0.7036210317460321, "naucs_at_3_max": 0.17889822595705038, "naucs_at_3_std": -0.12530345471521812, "naucs_at_3_diff1": 0.6112044817927178, "naucs_at_5_max": 0.1788982259570549, "naucs_at_5_std": -0.12530345471521045, "naucs_at_5_diff1": 0.6112044817927212, "naucs_at_10_max": -0.5929038281979383, "naucs_at_10_std": -0.5929038281979383, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": -1.7399626517273863, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "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 %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "model_max_length": 32768,
138
+ "pad_token": "<|endoftext|>",
139
+ "padding_side": "left",
140
+ "processor_class": "ColQwen2Processor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }
training_config.yml ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config:
2
+ (): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
3
+ output_dir: !path ../../../models/colqwen2-5e
4
+ processor:
5
+ (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
6
+ class_to_instanciate: !ext colpali_engine.models.ColQwen2Processor
7
+ pretrained_model_name_or_path: "./models/colqwen2_base" # "./models/paligemma-3b-mix-448"
8
+ # max_length: 50
9
+
10
+ model:
11
+ (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
12
+ class_to_instanciate: !ext colpali_engine.models.ColQwen2
13
+ pretrained_model_name_or_path: "./models/colqwen2_base"
14
+ torch_dtype: !ext torch.bfloat16
15
+ use_cache: false
16
+ # device_map: "auto"
17
+ # quantization_config:
18
+ # (): transformers.BitsAndBytesConfig
19
+ # load_in_4bit: true
20
+ # bnb_4bit_quant_type: "nf4"
21
+ # bnb_4bit_compute_dtype: "bfloat16"
22
+ # bnb_4bit_use_double_quant: true
23
+
24
+ dataset_loading_func: !ext colpali_engine.utils.dataset_transformation.load_train_set_detailed
25
+ eval_dataset_loader: !import ../data/test_data.yaml
26
+
27
+ # max_length: 50
28
+ run_eval: true
29
+ add_suffix: true
30
+ loss_func:
31
+ (): colpali_engine.loss.late_interaction_losses.ColbertPairwiseCELoss
32
+ tr_args:
33
+ (): transformers.training_args.TrainingArguments
34
+ output_dir: null
35
+ overwrite_output_dir: true
36
+ num_train_epochs: 5
37
+ per_device_train_batch_size: 4
38
+ # 6 x 8 gpus = 48 batch size
39
+ # gradient_accumulation_steps: 4
40
+ per_device_eval_batch_size: 4
41
+ eval_strategy: "steps"
42
+ # dataloader_num_workers: 8
43
+ # bf16: true
44
+ save_steps: 500
45
+ logging_steps: 10
46
+ eval_steps: 100
47
+ warmup_steps: 500
48
+ learning_rate: 5e-5
49
+ save_total_limit: 1
50
+ resume_from_checkpoint: true
51
+ # optim: "paged_adamw_8bit"
52
+
53
+ peft_config:
54
+ (): peft.LoraConfig
55
+ r: 32
56
+ lora_alpha: 32
57
+ lora_dropout: 0.1
58
+ init_lora_weights: "gaussian"
59
+ bias: "none"
60
+ task_type: "FEATURE_EXTRACTION"
61
+ target_modules: '(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
62
+ # target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
63
+
vocab.json ADDED
The diff for this file is too large to render. See raw diff