Markgazol commited on
Commit
8c0e93b
·
verified ·
1 Parent(s): a7ef3dd

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
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-VL-3B-Instruct
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": "Qwen/Qwen2.5-VL-3B-Instruct",
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": 128,
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": 128,
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 sha256:9232748e7d1c1c73f4e1071b5c44f47459121b8887e797fb9a167332f9ac7d65
3
+ size 479563360
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
+ 62bc8d64aae6fa0b612386af8c65b9f6debffd40
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_5Processor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"arxivqa_subsampled": {"ndcg_at_1": 0.88, "ndcg_at_3": 0.91676, "ndcg_at_5": 0.92244, "ndcg_at_10": 0.92694, "ndcg_at_20": 0.92951, "ndcg_at_100": 0.93352, "ndcg_at_1000": 0.93352, "map_at_1": 0.88, "map_at_3": 0.908, "map_at_5": 0.9111, "map_at_10": 0.91295, "map_at_20": 0.91368, "map_at_100": 0.91434, "map_at_1000": 0.91434, "recall_at_1": 0.88, "recall_at_3": 0.942, "recall_at_5": 0.956, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.88, "precision_at_3": 0.314, "precision_at_5": 0.1912, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.88, "mrr_at_3": 0.9079999999999999, "mrr_at_5": 0.9107999999999998, "mrr_at_10": 0.9130079365079364, "mrr_at_20": 0.9138274518738912, "mrr_at_100": 0.9143900697712918, "mrr_at_1000": 0.9143900697712918, "naucs_at_1_max": 0.782341711740376, "naucs_at_1_std": -0.14517181037225524, "naucs_at_1_diff1": 0.9443207126948777, "naucs_at_3_max": 0.8482887407836682, "naucs_at_3_std": -0.08648056923919158, "naucs_at_3_diff1": 0.9459093982420557, "naucs_at_5_max": 0.9032340208810806, "naucs_at_5_std": 0.05192683133859547, "naucs_at_5_diff1": 0.9524658348187762, "naucs_at_10_max": 0.8853096794273262, "naucs_at_10_std": -0.17223778400249365, "naucs_at_10_diff1": 0.9564270152505474, "naucs_at_20_max": 0.8949579831932757, "naucs_at_20_std": 0.0233893557422963, "naucs_at_20_diff1": 0.9607843137254862, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.54989, "ndcg_at_3": 0.6272, "ndcg_at_5": 0.64447, "ndcg_at_10": 0.66722, "ndcg_at_20": 0.68113, "ndcg_at_100": 0.69422, "ndcg_at_1000": 0.70437, "map_at_1": 0.54989, "map_at_3": 0.60865, "map_at_5": 0.61818, "map_at_10": 0.62746, "map_at_20": 0.63122, "map_at_100": 0.63287, "map_at_1000": 0.63328, "recall_at_1": 0.54989, "recall_at_3": 0.68071, "recall_at_5": 0.72284, "recall_at_10": 0.79379, "recall_at_20": 0.84922, "recall_at_100": 0.92239, "recall_at_1000": 1.0, "precision_at_1": 0.54989, "precision_at_3": 0.2269, "precision_at_5": 0.14457, "precision_at_10": 0.07938, "precision_at_20": 0.04246, "precision_at_100": 0.00922, "precision_at_1000": 0.001, "mrr_at_1": 0.5587583148558758, "mrr_at_3": 0.6130820399113082, "mrr_at_5": 0.6231707317073171, "mrr_at_10": 0.6318692147960442, "mrr_at_20": 0.6354293062372974, "mrr_at_100": 0.6373227650448284, "mrr_at_1000": 0.637754578561162, "naucs_at_1_max": 0.6626446233829012, "naucs_at_1_std": 0.02058080661271672, "naucs_at_1_diff1": 0.8687412101807956, "naucs_at_3_max": 0.6794601721961877, "naucs_at_3_std": 0.06185764496543819, "naucs_at_3_diff1": 0.7728703329559015, "naucs_at_5_max": 0.6676424400555316, "naucs_at_5_std": 0.12888850524239007, "naucs_at_5_diff1": 0.7580804398339002, "naucs_at_10_max": 0.6389757378756173, "naucs_at_10_std": 0.32256488584252335, "naucs_at_10_diff1": 0.744102835781862, "naucs_at_20_max": 0.6224489347919718, "naucs_at_20_std": 0.5363125392531453, "naucs_at_20_diff1": 0.7175713575781184, "naucs_at_100_max": 0.6404116660832495, "naucs_at_100_std": 0.7094528544475855, "naucs_at_100_diff1": 0.7671064727074209, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "infovqa_subsampled": {"ndcg_at_1": 0.89676, "ndcg_at_3": 0.92965, "ndcg_at_5": 0.93471, "ndcg_at_10": 0.93678, "ndcg_at_20": 0.93888, "ndcg_at_100": 0.94181, "ndcg_at_1000": 0.94261, "map_at_1": 0.89676, "map_at_3": 0.92206, "map_at_5": 0.9249, "map_at_10": 0.92581, "map_at_20": 0.92642, "map_at_100": 0.92679, "map_at_1000": 0.92683, "recall_at_1": 0.89676, "recall_at_3": 0.95142, "recall_at_5": 0.96356, "recall_at_10": 0.96964, "recall_at_20": 0.97773, "recall_at_100": 0.99393, "recall_at_1000": 1.0, "precision_at_1": 0.89676, "precision_at_3": 0.31714, "precision_at_5": 0.19271, "precision_at_10": 0.09696, "precision_at_20": 0.04889, "precision_at_100": 0.00994, "precision_at_1000": 0.001, "mrr_at_1": 0.8967611336032388, "mrr_at_3": 0.9217273954116058, "mrr_at_5": 0.9245614035087718, "mrr_at_10": 0.9254771544245227, "mrr_at_20": 0.9260782045611765, "mrr_at_100": 0.9264483101466887, "mrr_at_1000": 0.9264798727472631, "naucs_at_1_max": 0.6109225337520844, "naucs_at_1_std": -0.28746226687710974, "naucs_at_1_diff1": 0.9377884442360623, "naucs_at_3_max": 0.7513425815887516, "naucs_at_3_std": -0.1831182034901586, "naucs_at_3_diff1": 0.9448939012384912, "naucs_at_5_max": 0.8499324771117274, "naucs_at_5_std": 0.1674786026708613, "naucs_at_5_diff1": 0.9410364743251854, "naucs_at_10_max": 0.8460392633470242, "naucs_at_10_std": 0.26520856149085326, "naucs_at_10_diff1": 0.9292437691902227, "naucs_at_20_max": 0.8964958869122784, "naucs_at_20_std": 0.4196427770061891, "naucs_at_20_diff1": 0.927259949634811, "naucs_at_100_max": 0.9564661819784259, "naucs_at_100_std": 0.39174816052979483, "naucs_at_100_diff1": 0.9564661819784259, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.88571, "ndcg_at_3": 0.92704, "ndcg_at_5": 0.93749, "ndcg_at_10": 0.942, "ndcg_at_20": 0.94297, "ndcg_at_100": 0.94297, "ndcg_at_1000": 0.94297, "map_at_1": 0.88571, "map_at_3": 0.91667, "map_at_5": 0.92256, "map_at_10": 0.92436, "map_at_20": 0.92465, "map_at_100": 0.92465, "map_at_1000": 0.92465, "recall_at_1": 0.88571, "recall_at_3": 0.95714, "recall_at_5": 0.98214, "recall_at_10": 0.99643, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.88571, "precision_at_3": 0.31905, "precision_at_5": 0.19643, "precision_at_10": 0.09964, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.8892857142857142, "mrr_at_3": 0.917261904761905, "mrr_at_5": 0.9240476190476191, "mrr_at_10": 0.9258432539682538, "mrr_at_20": 0.9261408730158731, "mrr_at_100": 0.9261408730158731, "mrr_at_1000": 0.9261408730158731, "naucs_at_1_max": 0.6158489558614146, "naucs_at_1_std": 0.3338573801613662, "naucs_at_1_diff1": 0.8969209776934031, "naucs_at_3_max": 0.8942187986305661, "naucs_at_3_std": 0.6969732337379421, "naucs_at_3_diff1": 0.8620837223778431, "naucs_at_5_max": 0.9738562091503306, "naucs_at_5_std": 0.7899159663865564, "naucs_at_5_diff1": 0.8585434173669502, "naucs_at_10_max": 1.0, "naucs_at_10_std": 0.35807656395890114, "naucs_at_10_diff1": 0.8692810457516478, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "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": 0.68287, "ndcg_at_3": 0.78314, "ndcg_at_5": 0.80681, "ndcg_at_10": 0.82018, "ndcg_at_20": 0.82459, "ndcg_at_100": 0.82908, "ndcg_at_1000": 0.83033, "map_at_1": 0.68287, "map_at_3": 0.75932, "map_at_5": 0.77253, "map_at_10": 0.77817, "map_at_20": 0.77936, "map_at_100": 0.78001, "map_at_1000": 0.78007, "recall_at_1": 0.68287, "recall_at_3": 0.85176, "recall_at_5": 0.90887, "recall_at_10": 0.94957, "recall_at_20": 0.96719, "recall_at_100": 0.99089, "recall_at_1000": 1.0, "precision_at_1": 0.68287, "precision_at_3": 0.28392, "precision_at_5": 0.18177, "precision_at_10": 0.09496, "precision_at_20": 0.04836, "precision_at_100": 0.00991, "precision_at_1000": 0.001, "mrr_at_1": 0.6828675577156743, "mrr_at_3": 0.760024301336574, "mrr_at_5": 0.7729040097205355, "mrr_at_10": 0.7787074003355903, "mrr_at_20": 0.77981048225919, "mrr_at_100": 0.7804686644236308, "mrr_at_1000": 0.780530417746667, "naucs_at_1_max": 0.24316282742534667, "naucs_at_1_std": -0.2387486728504555, "naucs_at_1_diff1": 0.826824088265965, "naucs_at_3_max": 0.2785431946829428, "naucs_at_3_std": -0.21874668661261307, "naucs_at_3_diff1": 0.7258821333794314, "naucs_at_5_max": 0.37017261736106777, "naucs_at_5_std": -0.08964377104816615, "naucs_at_5_diff1": 0.6751762634115527, "naucs_at_10_max": 0.40798144776696565, "naucs_at_10_std": 0.0749134175280517, "naucs_at_10_diff1": 0.6195155652340053, "naucs_at_20_max": 0.3854116148741947, "naucs_at_20_std": 0.13880928341137488, "naucs_at_20_diff1": 0.6123683933054809, "naucs_at_100_max": 0.4016547830791494, "naucs_at_100_std": 0.3369662663486349, "naucs_at_100_diff1": 0.5452087419859556, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.78, "ndcg_at_3": 0.86309, "ndcg_at_5": 0.88375, "ndcg_at_10": 0.88708, "ndcg_at_20": 0.88979, "ndcg_at_100": 0.89155, "ndcg_at_1000": 0.89155, "map_at_1": 0.78, "map_at_3": 0.84333, "map_at_5": 0.85483, "map_at_10": 0.85626, "map_at_20": 0.8571, "map_at_100": 0.8573, "map_at_1000": 0.8573, "recall_at_1": 0.78, "recall_at_3": 0.92, "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": 0.78, "precision_at_3": 0.30667, "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": 0.79, "mrr_at_3": 0.8516666666666667, "mrr_at_5": 0.8636666666666667, "mrr_at_10": 0.8636666666666667, "mrr_at_20": 0.8643809523809525, "mrr_at_100": 0.8645850340136054, "mrr_at_1000": 0.8645850340136054, "naucs_at_1_max": -0.053646775165762495, "naucs_at_1_std": -0.4592664719246995, "naucs_at_1_diff1": 0.8246394955255713, "naucs_at_3_max": 0.3510154061624642, "naucs_at_3_std": 0.11437908496732017, "naucs_at_3_diff1": 0.7782446311858068, "naucs_at_5_max": 0.5169623404917556, "naucs_at_5_std": -0.22362278244631117, "naucs_at_5_diff1": 0.9074074074074108, "naucs_at_10_max": 0.27544351073763346, "naucs_at_10_std": -0.3968253968253954, "naucs_at_10_diff1": 0.861111111111116, "naucs_at_20_max": 0.7222222222222276, "naucs_at_20_std": 0.35807656395891135, "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": 0.985, "ndcg_at_5": 0.98931, "ndcg_at_10": 0.98931, "ndcg_at_20": 0.98931, "ndcg_at_100": 0.98931, "ndcg_at_1000": 0.98931, "map_at_1": 0.98, "map_at_3": 0.98333, "map_at_5": 0.98583, "map_at_10": 0.98583, "map_at_20": 0.98583, "map_at_100": 0.98583, "map_at_1000": 0.98583, "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": 0.9833333333333334, "mrr_at_5": 0.9858333333333335, "mrr_at_10": 0.9858333333333335, "mrr_at_20": 0.9858333333333335, "mrr_at_100": 0.9858333333333335, "mrr_at_1000": 0.9858333333333335, "naucs_at_1_max": 0.9346405228758133, "naucs_at_1_std": 0.41433239962652196, "naucs_at_1_diff1": 0.9346405228758133, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 0.8692810457516356, "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_energy": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.96024, "ndcg_at_5": 0.96454, "ndcg_at_10": 0.96454, "ndcg_at_20": 0.96454, "ndcg_at_100": 0.96658, "ndcg_at_1000": 0.96658, "map_at_1": 0.93, "map_at_3": 0.95333, "map_at_5": 0.95583, "map_at_10": 0.95583, "map_at_20": 0.95583, "map_at_100": 0.95618, "map_at_1000": 0.95618, "recall_at_1": 0.93, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.93, "precision_at_3": 0.32667, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.95, "mrr_at_3": 0.9633333333333333, "mrr_at_5": 0.9658333333333333, "mrr_at_10": 0.9658333333333333, "mrr_at_20": 0.9658333333333333, "mrr_at_100": 0.9662333333333332, "mrr_at_1000": 0.9662333333333332, "naucs_at_1_max": 0.625917033480058, "naucs_at_1_std": -0.5382819794584509, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 0.8611111111111119, "naucs_at_3_std": -0.2987861811391324, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": -1.1517273576097316, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": -1.1517273576097316, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": -1.1517273576097316, "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": 0.91, "ndcg_at_3": 0.96417, "ndcg_at_5": 0.96417, "ndcg_at_10": 0.96417, "ndcg_at_20": 0.96417, "ndcg_at_100": 0.96417, "ndcg_at_1000": 0.96417, "map_at_1": 0.91, "map_at_3": 0.95167, "map_at_5": 0.95167, "map_at_10": 0.95167, "map_at_20": 0.95167, "map_at_100": 0.95167, "map_at_1000": 0.95167, "recall_at_1": 0.91, "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": 0.91, "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": 0.91, "mrr_at_3": 0.9533333333333335, "mrr_at_5": 0.9533333333333335, "mrr_at_10": 0.9533333333333335, "mrr_at_20": 0.9533333333333335, "mrr_at_100": 0.9533333333333335, "mrr_at_1000": 0.9533333333333335, "naucs_at_1_max": 0.8433447453055296, "naucs_at_1_std": 0.24981844589687535, "naucs_at_1_diff1": 0.9564270152505436, "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_healthcare_industry": {"ndcg_at_1": 0.96, "ndcg_at_3": 0.98393, "ndcg_at_5": 0.98393, "ndcg_at_10": 0.98393, "ndcg_at_20": 0.98393, "ndcg_at_100": 0.98393, "ndcg_at_1000": 0.98393, "map_at_1": 0.96, "map_at_3": 0.97833, "map_at_5": 0.97833, "map_at_10": 0.97833, "map_at_20": 0.97833, "map_at_100": 0.97833, "map_at_1000": 0.97833, "recall_at_1": 0.96, "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": 0.96, "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": 0.96, "mrr_at_3": 0.9783333333333334, "mrr_at_5": 0.9783333333333334, "mrr_at_10": 0.9783333333333334, "mrr_at_20": 0.9783333333333334, "mrr_at_100": 0.9783333333333334, "mrr_at_1000": 0.9783333333333334, "naucs_at_1_max": 0.7496498599439807, "naucs_at_1_std": -0.19304388422035748, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_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
@@ -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 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_5Processor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
training_config.yml ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config:
2
+ (): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
3
+ output_dir: !path ../../../models/colqwen2_5
4
+ processor:
5
+ (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
6
+ class_to_instanciate: !ext colpali_engine.models.ColQwen2_5Processor
7
+ pretrained_model_name_or_path: "Qwen/Qwen2.5-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: "Qwen/Qwen2.5-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_mixed_train_set
27
+ eval_dataset_loader: !import ../data/test_data.yaml
28
+ pretrained_peft_model_name_or_path: models/colqwen2.5-3b-multilingual/checkpoint-1800
29
+
30
+ # max_length: 50
31
+ run_eval: true
32
+ loss_func:
33
+ (): colpali_engine.loss.late_interaction_losses.ColbertPairwiseCELoss
34
+ tr_args:
35
+ (): transformers.training_args.TrainingArguments
36
+ output_dir: null
37
+ overwrite_output_dir: true
38
+ num_train_epochs: 3
39
+ per_device_train_batch_size: 64
40
+ gradient_checkpointing: true
41
+ gradient_checkpointing_kwargs: { "use_reentrant": false }
42
+ # gradient_checkpointing: true
43
+ # 6 x 8 gpus = 48 batch size
44
+ gradient_accumulation_steps: 2
45
+ per_device_eval_batch_size: 32
46
+ eval_strategy: "steps"
47
+ dataloader_num_workers: 8
48
+ # bf16: true
49
+ save_steps: 100
50
+ logging_steps: 1
51
+ eval_steps: 400
52
+ warmup_steps: 100
53
+ learning_rate: 8e-5
54
+ save_total_limit: 15
55
+ resume_from_checkpoint: false
56
+ # optim: "paged_adamw"
57
+ # wandb logging
58
+ # wandb_project: "dolma"
59
+ run_name: "colqwen2_5"
60
+ report_to: wandb
61
+
62
+
63
+ peft_config:
64
+ (): peft.LoraConfig
65
+ r: 128
66
+ lora_alpha: 128
67
+ lora_dropout: 0.1
68
+ init_lora_weights: "gaussian"
69
+ bias: "none"
70
+ task_type: "FEATURE_EXTRACTION"
71
+ target_modules: '(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
72
+ # target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
73
+
vocab.json ADDED
The diff for this file is too large to render. See raw diff