Markgazol commited on
Commit
a19ef03
·
verified ·
1 Parent(s): 0da38ca

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: ./models/qwenstella-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": "./models/qwenstella-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": 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).*$|.*(vector_linear_1024).*$|.*(vision_model).*(merger).*(mlp).*(0|2).*$)",
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 sha256:73aaa9e14349f0237c69d8cac997c9d9c3da25c92d89c068f721739caaedc3ae
3
+ size 300471232
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
+ 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": "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": "ColQwenStellaProcessor",
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
+ {"arxivqa_subsampled": {"ndcg_at_1": 0.846, "ndcg_at_3": 0.88724, "ndcg_at_5": 0.89464, "ndcg_at_10": 0.90262, "ndcg_at_20": 0.90655, "ndcg_at_100": 0.91016, "ndcg_at_1000": 0.91096, "map_at_1": 0.846, "map_at_3": 0.87667, "map_at_5": 0.88077, "map_at_10": 0.88419, "map_at_20": 0.88522, "map_at_100": 0.88582, "map_at_1000": 0.88586, "recall_at_1": 0.846, "recall_at_3": 0.918, "recall_at_5": 0.936, "recall_at_10": 0.96, "recall_at_20": 0.976, "recall_at_100": 0.994, "recall_at_1000": 1.0, "precision_at_1": 0.846, "precision_at_3": 0.306, "precision_at_5": 0.1872, "precision_at_10": 0.096, "precision_at_20": 0.0488, "precision_at_100": 0.00994, "precision_at_1000": 0.001, "mrr_at_1": 0.846, "mrr_at_3": 0.8763333333333332, "mrr_at_5": 0.8814333333333333, "mrr_at_10": 0.8845722222222221, "mrr_at_20": 0.885592790130406, "mrr_at_100": 0.8862097092529907, "mrr_at_1000": 0.8862427513676859, "naucs_at_1_max": 0.7479507415456175, "naucs_at_1_std": -0.2812281571288769, "naucs_at_1_diff1": 0.9258454382553668, "naucs_at_3_max": 0.8387761608708549, "naucs_at_3_std": -0.24216027874564358, "naucs_at_3_diff1": 0.8901755824280918, "naucs_at_5_max": 0.8996265172735749, "naucs_at_5_std": -0.2175390989729223, "naucs_at_5_diff1": 0.8941555788982243, "naucs_at_10_max": 0.9303221288515416, "naucs_at_10_std": -0.2065126050420224, "naucs_at_10_diff1": 0.8937908496732003, "naucs_at_20_max": 0.928804855275447, "naucs_at_20_std": -0.11896981014628347, "naucs_at_20_diff1": 0.9114923747276666, "naucs_at_100_max": 1.0, "naucs_at_100_std": 0.18643012760655897, "naucs_at_100_diff1": 0.9128540305010608, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.53437, "ndcg_at_3": 0.60632, "ndcg_at_5": 0.62646, "ndcg_at_10": 0.64874, "ndcg_at_20": 0.65909, "ndcg_at_100": 0.67792, "ndcg_at_1000": 0.6888, "map_at_1": 0.53437, "map_at_3": 0.58832, "map_at_5": 0.59952, "map_at_10": 0.60875, "map_at_20": 0.61173, "map_at_100": 0.61445, "map_at_1000": 0.61488, "recall_at_1": 0.53437, "recall_at_3": 0.65854, "recall_at_5": 0.70732, "recall_at_10": 0.77605, "recall_at_20": 0.81596, "recall_at_100": 0.91574, "recall_at_1000": 1.0, "precision_at_1": 0.53437, "precision_at_3": 0.21951, "precision_at_5": 0.14146, "precision_at_10": 0.07761, "precision_at_20": 0.0408, "precision_at_100": 0.00916, "precision_at_1000": 0.001, "mrr_at_1": 0.5365853658536586, "mrr_at_3": 0.5901699926090171, "mrr_at_5": 0.6021433850702144, "mrr_at_10": 0.6104872769506914, "mrr_at_20": 0.6132983422271759, "mrr_at_100": 0.6160294924799838, "mrr_at_1000": 0.6163830410583075, "naucs_at_1_max": 0.5973701491411594, "naucs_at_1_std": 0.15100454385637924, "naucs_at_1_diff1": 0.8982591944341096, "naucs_at_3_max": 0.4757723580757023, "naucs_at_3_std": 0.22070278027542517, "naucs_at_3_diff1": 0.8195064617583738, "naucs_at_5_max": 0.4575723188898858, "naucs_at_5_std": 0.3134827125035666, "naucs_at_5_diff1": 0.8072241700536605, "naucs_at_10_max": 0.4266102606041783, "naucs_at_10_std": 0.4518654327173679, "naucs_at_10_diff1": 0.7860743297872201, "naucs_at_20_max": 0.3739263641054462, "naucs_at_20_std": 0.5739789303935408, "naucs_at_20_diff1": 0.7911193147059952, "naucs_at_100_max": 0.07709889473305605, "naucs_at_100_std": 0.9164818709731807, "naucs_at_100_diff1": 0.7582525989589187, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "infovqa_subsampled": {"ndcg_at_1": 0.88462, "ndcg_at_3": 0.9157, "ndcg_at_5": 0.92136, "ndcg_at_10": 0.92762, "ndcg_at_20": 0.92974, "ndcg_at_100": 0.93344, "ndcg_at_1000": 0.93371, "map_at_1": 0.88462, "map_at_3": 0.90823, "map_at_5": 0.91127, "map_at_10": 0.91407, "map_at_20": 0.91469, "map_at_100": 0.91517, "map_at_1000": 0.91519, "recall_at_1": 0.88462, "recall_at_3": 0.93725, "recall_at_5": 0.95142, "recall_at_10": 0.96964, "recall_at_20": 0.97773, "recall_at_100": 0.99798, "recall_at_1000": 1.0, "precision_at_1": 0.88462, "precision_at_3": 0.31242, "precision_at_5": 0.19028, "precision_at_10": 0.09696, "precision_at_20": 0.04889, "precision_at_100": 0.00998, "precision_at_1000": 0.001, "mrr_at_1": 0.8846153846153846, "mrr_at_3": 0.9078947368421051, "mrr_at_5": 0.9119433198380564, "mrr_at_10": 0.9141242529400422, "mrr_at_20": 0.9149161960396777, "mrr_at_100": 0.9153930732357304, "mrr_at_1000": 0.9154058852072365, "naucs_at_1_max": 0.6190259976448219, "naucs_at_1_std": -0.3264770605196707, "naucs_at_1_diff1": 0.9262796600708453, "naucs_at_3_max": 0.781416166586695, "naucs_at_3_std": -0.12104903138475114, "naucs_at_3_diff1": 0.9081894684511614, "naucs_at_5_max": 0.8767035503045449, "naucs_at_5_std": 0.10481623478693029, "naucs_at_5_diff1": 0.9038671319947321, "naucs_at_10_max": 0.9354592911852186, "naucs_at_10_std": 0.25907731302868264, "naucs_at_10_diff1": 0.9390526547697702, "naucs_at_20_max": 0.9238628019857293, "naucs_at_20_std": 0.30347513687216277, "naucs_at_20_diff1": 0.928762843237398, "naucs_at_100_max": 0.8693985459351681, "naucs_at_100_std": 0.12265766416441783, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.90357, "ndcg_at_3": 0.94405, "ndcg_at_5": 0.95127, "ndcg_at_10": 0.95365, "ndcg_at_20": 0.95365, "ndcg_at_100": 0.9544, "ndcg_at_1000": 0.9544, "map_at_1": 0.90357, "map_at_3": 0.93452, "map_at_5": 0.93845, "map_at_10": 0.93947, "map_at_20": 0.93947, "map_at_100": 0.93961, "map_at_1000": 0.93961, "recall_at_1": 0.90357, "recall_at_3": 0.97143, "recall_at_5": 0.98929, "recall_at_10": 0.99643, "recall_at_20": 0.99643, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.90357, "precision_at_3": 0.32381, "precision_at_5": 0.19786, "precision_at_10": 0.09964, "precision_at_20": 0.04982, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.9035714285714286, "mrr_at_3": 0.9345238095238096, "mrr_at_5": 0.9384523809523809, "mrr_at_10": 0.9394090136054422, "mrr_at_20": 0.9394090136054422, "mrr_at_100": 0.9395463762428049, "mrr_at_1000": 0.9395463762428049, "naucs_at_1_max": 0.5883217484524678, "naucs_at_1_std": 0.046685340802988085, "naucs_at_1_diff1": 0.8713559497873212, "naucs_at_3_max": 0.822945845004673, "naucs_at_3_std": 0.5123716153127884, "naucs_at_3_diff1": 0.9305555555555513, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.9128540305011011, "naucs_at_5_diff1": 0.9074074074074161, "naucs_at_10_max": 1.0, "naucs_at_10_std": 0.8692810457516478, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 0.8692810457516478, "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": 0.66221, "ndcg_at_3": 0.7618, "ndcg_at_5": 0.78695, "ndcg_at_10": 0.80524, "ndcg_at_20": 0.81008, "ndcg_at_100": 0.81541, "ndcg_at_1000": 0.81634, "map_at_1": 0.66221, "map_at_3": 0.73815, "map_at_5": 0.75204, "map_at_10": 0.75983, "map_at_20": 0.7612, "map_at_100": 0.76198, "map_at_1000": 0.76203, "recall_at_1": 0.66221, "recall_at_3": 0.82989, "recall_at_5": 0.89125, "recall_at_10": 0.94654, "recall_at_20": 0.96537, "recall_at_100": 0.99332, "recall_at_1000": 1.0, "precision_at_1": 0.66221, "precision_at_3": 0.27663, "precision_at_5": 0.17825, "precision_at_10": 0.09465, "precision_at_20": 0.04827, "precision_at_100": 0.00993, "precision_at_1000": 0.001, "mrr_at_1": 0.6591737545565006, "mrr_at_3": 0.7368367760226815, "mrr_at_5": 0.750901174564602, "mrr_at_10": 0.7581910933672786, "mrr_at_20": 0.7596198059062583, "mrr_at_100": 0.7604221238767853, "mrr_at_1000": 0.7604672192997383, "naucs_at_1_max": 0.27078275465894486, "naucs_at_1_std": -0.2663234396116274, "naucs_at_1_diff1": 0.8294043992382637, "naucs_at_3_max": 0.330441662626675, "naucs_at_3_std": -0.18926582210411605, "naucs_at_3_diff1": 0.7259080195940506, "naucs_at_5_max": 0.36775785913157905, "naucs_at_5_std": -0.08929087499088985, "naucs_at_5_diff1": 0.7091864349746133, "naucs_at_10_max": 0.5108967532379013, "naucs_at_10_std": 0.10663319614120796, "naucs_at_10_diff1": 0.7206260108568603, "naucs_at_20_max": 0.6726089047927092, "naucs_at_20_std": 0.36289839721701594, "naucs_at_20_diff1": 0.7442189535318923, "naucs_at_100_max": 0.6921321331042545, "naucs_at_100_std": 0.7999774728465878, "naucs_at_100_diff1": 0.6295641820467829, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.75, "ndcg_at_3": 0.86833, "ndcg_at_5": 0.88081, "ndcg_at_10": 0.88382, "ndcg_at_20": 0.88382, "ndcg_at_100": 0.88543, "ndcg_at_1000": 0.88543, "map_at_1": 0.75, "map_at_3": 0.84, "map_at_5": 0.847, "map_at_10": 0.84811, "map_at_20": 0.84811, "map_at_100": 0.84825, "map_at_1000": 0.84825, "recall_at_1": 0.75, "recall_at_3": 0.95, "recall_at_5": 0.98, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.75, "precision_at_3": 0.31667, "precision_at_5": 0.196, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.74, "mrr_at_3": 0.8333333333333331, "mrr_at_5": 0.8423333333333332, "mrr_at_10": 0.8434444444444443, "mrr_at_20": 0.8434444444444443, "mrr_at_100": 0.8435795795795795, "mrr_at_1000": 0.8435795795795795, "naucs_at_1_max": 0.11870225013082168, "naucs_at_1_std": -0.40613291470434393, "naucs_at_1_diff1": 0.8483516483516487, "naucs_at_3_max": 0.09925303454715217, "naucs_at_3_std": -0.3987861811391193, "naucs_at_3_diff1": 0.7955182072829138, "naucs_at_5_max": 0.3384687208216692, "naucs_at_5_std": 0.09337068160597826, "naucs_at_5_diff1": 0.7770774976657324, "naucs_at_10_max": 0.5541549953314738, "naucs_at_10_std": 0.35807656395891135, "naucs_at_10_diff1": 0.5541549953314738, "naucs_at_20_max": 0.5541549953314738, "naucs_at_20_std": 0.35807656395891135, "naucs_at_20_diff1": 0.5541549953314738, "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": 0.99, "ndcg_at_3": 0.99631, "ndcg_at_5": 0.99631, "ndcg_at_10": 0.99631, "ndcg_at_20": 0.99631, "ndcg_at_100": 0.99631, "ndcg_at_1000": 0.99631, "map_at_1": 0.99, "map_at_3": 0.995, "map_at_5": 0.995, "map_at_10": 0.995, "map_at_20": 0.995, "map_at_100": 0.995, "map_at_1000": 0.995, "recall_at_1": 0.99, "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": 0.99, "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": 0.99, "mrr_at_3": 0.995, "mrr_at_5": 0.995, "mrr_at_10": 0.995, "mrr_at_20": 0.995, "mrr_at_100": 0.995, "mrr_at_1000": 0.995, "naucs_at_1_max": 1.0, "naucs_at_1_std": 1.0, "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}, "syntheticDocQA_energy": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.94655, "ndcg_at_5": 0.95428, "ndcg_at_10": 0.95428, "ndcg_at_20": 0.95428, "ndcg_at_100": 0.95636, "ndcg_at_1000": 0.95636, "map_at_1": 0.91, "map_at_3": 0.93833, "map_at_5": 0.94233, "map_at_10": 0.94233, "map_at_20": 0.94233, "map_at_100": 0.9427, "map_at_1000": 0.9427, "recall_at_1": 0.91, "recall_at_3": 0.97, "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": 0.91, "precision_at_3": 0.32333, "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": 0.91, "mrr_at_3": 0.94, "mrr_at_5": 0.9440000000000001, "mrr_at_10": 0.9440000000000001, "mrr_at_20": 0.9440000000000001, "mrr_at_100": 0.9443846153846154, "mrr_at_1000": 0.9443846153846154, "naucs_at_1_max": 0.13269011308227113, "naucs_at_1_std": -0.5395269218798633, "naucs_at_1_diff1": 0.9709513435003629, "naucs_at_3_max": 0.9564270152505466, "naucs_at_3_std": -0.2236227824463119, "naucs_at_3_diff1": 0.9564270152505466, "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": 0.94, "ndcg_at_3": 0.96262, "ndcg_at_5": 0.97079, "ndcg_at_10": 0.97079, "ndcg_at_20": 0.97079, "ndcg_at_100": 0.97079, "ndcg_at_1000": 0.97079, "map_at_1": 0.94, "map_at_3": 0.95667, "map_at_5": 0.96117, "map_at_10": 0.96117, "map_at_20": 0.96117, "map_at_100": 0.96117, "map_at_1000": 0.96117, "recall_at_1": 0.94, "recall_at_3": 0.98, "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": 0.94, "precision_at_3": 0.32667, "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": 0.9566666666666666, "mrr_at_5": 0.9611666666666666, "mrr_at_10": 0.9611666666666666, "mrr_at_20": 0.9611666666666666, "mrr_at_100": 0.9611666666666666, "mrr_at_1000": 0.9611666666666666, "naucs_at_1_max": 0.8576097105508863, "naucs_at_1_std": 0.32555244319950205, "naucs_at_1_diff1": 0.9101307189542497, "naucs_at_3_max": 0.7770774976657261, "naucs_at_3_std": 0.4143323996265135, "naucs_at_3_diff1": 0.8611111111111119, "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": 0.99, "ndcg_at_3": 0.99631, "ndcg_at_5": 0.99631, "ndcg_at_10": 0.99631, "ndcg_at_20": 0.99631, "ndcg_at_100": 0.99631, "ndcg_at_1000": 0.99631, "map_at_1": 0.99, "map_at_3": 0.995, "map_at_5": 0.995, "map_at_10": 0.995, "map_at_20": 0.995, "map_at_100": 0.995, "map_at_1000": 0.995, "recall_at_1": 0.99, "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": 0.99, "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": 0.99, "mrr_at_3": 0.995, "mrr_at_5": 0.995, "mrr_at_10": 0.995, "mrr_at_20": 0.995, "mrr_at_100": 0.995, "mrr_at_1000": 0.995, "naucs_at_1_max": 0.12278244631185359, "naucs_at_1_std": -1.151727357609709, "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 sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
3
+ size 11420538
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": "ColQwenStellaProcessor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }
training_config.yml ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config:
2
+ (): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
3
+ output_dir: !path ../../../models/qwenstella_8e-5_tabfquad_3e_cont_1e-5
4
+ processor:
5
+ (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
6
+ class_to_instanciate: !ext colpali_engine.models.ColQwenStellaProcessor
7
+ pretrained_model_name_or_path: "./models/qwenstella-base" #"vidore/colqwen2-base" #"./models/colqwen2-base" # "./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.ColQwenStella
14
+ pretrained_model_name_or_path: "./models/qwenstella-base" #"vidore/colqwen2-base" #"./models/colqwen2-base"
15
+ torch_dtype: !ext torch.bfloat16
16
+ # weights_only: false
17
+ # use_cache: false
18
+ attn_implementation: "flash_attention_2"
19
+ # device_map: "auto"
20
+ # quantization_config:
21
+ # (): transformers.BitsAndBytesConfig
22
+ # load_in_4bit: true
23
+ # bnb_4bit_quant_type: "nf4"
24
+ # bnb_4bit_compute_dtype: "bfloat16"
25
+ # bnb_4bit_use_double_quant: true
26
+
27
+ dataset_loading_func: !ext colpali_engine.utils.dataset_transformation.load_mixed_train_set
28
+ eval_dataset_loader: !import ../data/test_data.yaml
29
+ pretrained_peft_model_name_or_path: models/qwenstella_8e-5_tabfquad_3e
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: 5
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: 1e-5
54
+ save_total_limit: 100
55
+ lr_scheduler_type: cosine
56
+ # lr_scheduler_kwargs: min_lr
57
+ # resume_from_checkpoint: true
58
+ # optim: "paged_adamw_8bit"
59
+ # wandb logging
60
+ # wandb_name: "colqwen2"
61
+ run_name: "qwenstella_8e-5_tabfquad_3e_cont_1e-5"
62
+ report_to: "wandb"
63
+
64
+
65
+ peft_config:
66
+ (): peft.LoraConfig
67
+ r: 128
68
+ lora_alpha: 128
69
+ lora_dropout: 0.1
70
+ init_lora_weights: "gaussian"
71
+ bias: "none"
72
+ task_type: "FEATURE_EXTRACTION"
73
+ target_modules: "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(vector_linear_1024).*$|.*(vision_model).*(merger).*(mlp).*(0|2).*$)"
74
+ # target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
75
+
vocab.json ADDED
The diff for this file is too large to render. See raw diff