Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +202 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +16 -0
- chat_template.json +3 -0
- git_hash.txt +1 -0
- merges.txt +0 -0
- preprocessor_config.json +29 -0
- results.json +1 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +144 -0
- training_config.yml +73 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: vidore/colqwen2-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 sha256:9c980be51a87eb3a5ee3d7ef921f40a78335fdc9eb9d37b867a11e590d7a7113
|
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 |
+
8390a70d508cdac8bd9957611f428cebfba4845e
|
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": 0.842, "ndcg_at_3": 0.88607, "ndcg_at_5": 0.89166, "ndcg_at_10": 0.89809, "ndcg_at_20": 0.90151, "ndcg_at_50": 0.90388, "ndcg_at_100": 0.90649, "map_at_1": 0.842, "map_at_3": 0.87567, "map_at_5": 0.87867, "map_at_10": 0.8813, "map_at_20": 0.88218, "map_at_50": 0.88255, "map_at_100": 0.88279, "recall_at_1": 0.842, "recall_at_3": 0.916, "recall_at_5": 0.93, "recall_at_10": 0.95, "recall_at_20": 0.964, "recall_at_50": 0.976, "recall_at_100": 0.992, "precision_at_1": 0.842, "precision_at_3": 0.30533, "precision_at_5": 0.186, "precision_at_10": 0.095, "precision_at_20": 0.0482, "precision_at_50": 0.01952, "precision_at_100": 0.00992, "mrr_at_1": 0.846, "mrr_at_3": 0.878, "mrr_at_5": 0.8817999999999999, "mrr_at_10": 0.884202380952381, "mrr_at_20": 0.8851428457507404, "mrr_at_50": 0.8859005862850743, "mrr_at_100": 0.8859630560187304, "naucs_at_1_max": 0.14980322536592605, "naucs_at_1_std": 0.13490546127202088, "naucs_at_1_diff1": 0.9576655203664858, "naucs_at_3_max": -0.1255502200880325, "naucs_at_3_std": 0.4357854252812249, "naucs_at_3_diff1": 0.9442554799697651, "naucs_at_5_max": -0.18676804054955595, "naucs_at_5_std": 0.5007869814592494, "naucs_at_5_diff1": 0.9691876750700267, "naucs_at_10_max": -0.24179271708683783, "naucs_at_10_std": 0.5684407096171821, "naucs_at_10_diff1": 0.9732026143790856, "naucs_at_20_max": -0.3797333748314225, "naucs_at_20_std": 0.6160908807967637, "naucs_at_20_diff1": 0.985475671750177, "naucs_at_50_max": -0.709617180205425, "naucs_at_50_std": 0.7341269841269842, "naucs_at_50_diff1": 1.0, "naucs_at_100_max": -0.21755368814195147, "naucs_at_100_std": 0.9346405228758211, "naucs_at_100_diff1": 1.0}, "syntheticDocQA_energy": {"ndcg_at_1": 0.95, "ndcg_at_3": 0.96131, "ndcg_at_5": 0.96131, "ndcg_at_10": 0.96788, "ndcg_at_20": 0.9702, "ndcg_at_50": 0.9702, "ndcg_at_100": 0.9702, "map_at_1": 0.95, "map_at_3": 0.95833, "map_at_5": 0.95833, "map_at_10": 0.96111, "map_at_20": 0.96164, "map_at_50": 0.96164, "map_at_100": 0.96164, "recall_at_1": 0.95, "recall_at_3": 0.97, "recall_at_5": 0.97, "recall_at_10": 0.99, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.95, "precision_at_3": 0.32333, "precision_at_5": 0.194, "precision_at_10": 0.099, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.96, "mrr_at_3": 0.9633333333333333, "mrr_at_5": 0.9653333333333333, "mrr_at_10": 0.9664444444444444, "mrr_at_20": 0.9671587301587301, "mrr_at_50": 0.9671587301587301, "mrr_at_100": 0.9671587301587301, "naucs_at_1_max": 0.683099906629318, "naucs_at_1_std": -0.6536881419234336, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 0.664021164021167, "naucs_at_3_std": -1.21708683473389, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 0.6640211640211615, "naucs_at_5_std": -1.2170868347338937, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 0.8692810457516413, "naucs_at_10_std": -1.7399626517273863, "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_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.96, "ndcg_at_3": 0.98524, "ndcg_at_5": 0.98524, "ndcg_at_10": 0.98524, "ndcg_at_20": 0.98524, "ndcg_at_50": 0.98524, "ndcg_at_100": 0.98524, "map_at_1": 0.96, "map_at_3": 0.98, "map_at_5": 0.98, "map_at_10": 0.98, "map_at_20": 0.98, "map_at_50": 0.98, "map_at_100": 0.98, "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_50": 1.0, "recall_at_100": 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_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.96, "mrr_at_3": 0.98, "mrr_at_5": 0.98, "mrr_at_10": 0.98, "mrr_at_20": 0.98, "mrr_at_50": 0.98, "mrr_at_100": 0.98, "naucs_at_1_max": 0.8284313725490191, "naucs_at_1_std": -0.2200046685340767, "naucs_at_1_diff1": 0.96732026143791, "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_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.98, "ndcg_at_3": 0.99131, "ndcg_at_5": 0.99131, "ndcg_at_10": 0.99131, "ndcg_at_20": 0.99131, "ndcg_at_50": 0.99131, "ndcg_at_100": 0.99131, "map_at_1": 0.98, "map_at_3": 0.98833, "map_at_5": 0.98833, "map_at_10": 0.98833, "map_at_20": 0.98833, "map_at_50": 0.98833, "map_at_100": 0.98833, "recall_at_1": 0.98, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.98, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.98, "mrr_at_3": 0.9883333333333333, "mrr_at_5": 0.9883333333333333, "mrr_at_10": 0.9883333333333333, "mrr_at_20": 0.9883333333333333, "mrr_at_50": 0.9883333333333333, "mrr_at_100": 0.9883333333333333, "naucs_at_1_max": 0.8692810457516332, "naucs_at_1_std": -0.5088702147525628, "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_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.9, "ndcg_at_3": 0.95417, "ndcg_at_5": 0.95417, "ndcg_at_10": 0.95718, "ndcg_at_20": 0.95718, "ndcg_at_50": 0.95718, "ndcg_at_100": 0.95718, "map_at_1": 0.9, "map_at_3": 0.94167, "map_at_5": 0.94167, "map_at_10": 0.94278, "map_at_20": 0.94278, "map_at_50": 0.94278, "map_at_100": 0.94278, "recall_at_1": 0.9, "recall_at_3": 0.99, "recall_at_5": 0.99, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.9, "precision_at_3": 0.33, "precision_at_5": 0.198, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.9, "mrr_at_3": 0.9433333333333332, "mrr_at_5": 0.9433333333333332, "mrr_at_10": 0.9444444444444444, "mrr_at_20": 0.9444444444444444, "mrr_at_50": 0.9444444444444444, "mrr_at_100": 0.9444444444444444, "naucs_at_1_max": 0.6324463118580764, "naucs_at_1_std": 0.3140989729225021, "naucs_at_1_diff1": 0.9607843137254906, "naucs_at_3_max": 1.0, "naucs_at_3_std": 0.7222222222222157, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.7222222222222276, "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_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "infovqa_subsampled": {"ndcg_at_1": 0.884, "ndcg_at_3": 0.91245, "ndcg_at_5": 0.91968, "ndcg_at_10": 0.92228, "ndcg_at_20": 0.92482, "ndcg_at_50": 0.92647, "ndcg_at_100": 0.92777, "map_at_1": 0.884, "map_at_3": 0.90567, "map_at_5": 0.90957, "map_at_10": 0.91066, "map_at_20": 0.91135, "map_at_50": 0.91165, "map_at_100": 0.91176, "recall_at_1": 0.884, "recall_at_3": 0.932, "recall_at_5": 0.95, "recall_at_10": 0.958, "recall_at_20": 0.968, "recall_at_50": 0.976, "recall_at_100": 0.984, "precision_at_1": 0.884, "precision_at_3": 0.31067, "precision_at_5": 0.19, "precision_at_10": 0.0958, "precision_at_20": 0.0484, "precision_at_50": 0.01952, "precision_at_100": 0.00984, "mrr_at_1": 0.882, "mrr_at_3": 0.9043333333333333, "mrr_at_5": 0.9081333333333333, "mrr_at_10": 0.9092444444444444, "mrr_at_20": 0.9099755336167101, "mrr_at_50": 0.9102621834483599, "mrr_at_100": 0.9103823466185231, "naucs_at_1_max": 0.7065231646939233, "naucs_at_1_std": 0.05565756254303531, "naucs_at_1_diff1": 0.940899701629562, "naucs_at_3_max": 0.8456774866809487, "naucs_at_3_std": 0.30691492283187727, "naucs_at_3_diff1": 0.9336793540945822, "naucs_at_5_max": 0.941176470588235, "naucs_at_5_std": 0.46224089635854493, "naucs_at_5_diff1": 0.9313725490196085, "naucs_at_10_max": 0.942421413009648, "naucs_at_10_std": 0.4962651727357598, "naucs_at_10_diff1": 0.9245253657018353, "naucs_at_20_max": 0.9581290849673211, "naucs_at_20_std": 0.6626400560224076, "naucs_at_20_diff1": 0.917279411764704, "naucs_at_50_max": 0.978213507625274, "naucs_at_50_std": 0.8516184251478357, "naucs_at_50_diff1": 0.911492374727667, "naucs_at_100_max": 0.9673202614379109, "naucs_at_100_std": 0.8740079365079331, "naucs_at_100_diff1": 0.8672385620914999}, "docvqa_subsampled": {"ndcg_at_1": 0.482, "ndcg_at_3": 0.53638, "ndcg_at_5": 0.5566, "ndcg_at_10": 0.58035, "ndcg_at_20": 0.59013, "ndcg_at_50": 0.60114, "ndcg_at_100": 0.60886, "map_at_1": 0.482, "map_at_3": 0.52333, "map_at_5": 0.53433, "map_at_10": 0.54403, "map_at_20": 0.5468, "map_at_50": 0.54853, "map_at_100": 0.54919, "recall_at_1": 0.482, "recall_at_3": 0.574, "recall_at_5": 0.624, "recall_at_10": 0.698, "recall_at_20": 0.736, "recall_at_50": 0.792, "recall_at_100": 0.84, "precision_at_1": 0.482, "precision_at_3": 0.19133, "precision_at_5": 0.1248, "precision_at_10": 0.0698, "precision_at_20": 0.0368, "precision_at_50": 0.01584, "precision_at_100": 0.0084, "mrr_at_1": 0.476, "mrr_at_3": 0.5206666666666666, "mrr_at_5": 0.5325666666666667, "mrr_at_10": 0.5408849206349206, "mrr_at_20": 0.5443294747306358, "mrr_at_50": 0.5456530086612842, "mrr_at_100": 0.5466288691712617, "naucs_at_1_max": 0.11546090350805194, "naucs_at_1_std": 0.678213639746092, "naucs_at_1_diff1": 0.9150091230002886, "naucs_at_3_max": -0.006613409596074608, "naucs_at_3_std": 0.7932113091033843, "naucs_at_3_diff1": 0.8907490104390393, "naucs_at_5_max": -0.07645913914509621, "naucs_at_5_std": 0.8597608598631361, "naucs_at_5_diff1": 0.8752417435287114, "naucs_at_10_max": -0.18047119686299265, "naucs_at_10_std": 0.8799692900476072, "naucs_at_10_diff1": 0.8267973035513766, "naucs_at_20_max": -0.2529875372440978, "naucs_at_20_std": 0.888227661551276, "naucs_at_20_diff1": 0.8310159228526568, "naucs_at_50_max": -0.38866116247068644, "naucs_at_50_std": 0.8807246545341788, "naucs_at_50_diff1": 0.825517956470337, "naucs_at_100_max": -0.465617329405992, "naucs_at_100_std": 0.9135125184094256, "naucs_at_100_diff1": 0.8196305841924404}, "arxivqa_subsampled": {"ndcg_at_1": 0.842, "ndcg_at_3": 0.88255, "ndcg_at_5": 0.88935, "ndcg_at_10": 0.89974, "ndcg_at_20": 0.90386, "ndcg_at_50": 0.90791, "ndcg_at_100": 0.90858, "map_at_1": 0.842, "map_at_3": 0.873, "map_at_5": 0.8769, "map_at_10": 0.88121, "map_at_20": 0.88239, "map_at_50": 0.88307, "map_at_100": 0.88314, "recall_at_1": 0.842, "recall_at_3": 0.91, "recall_at_5": 0.926, "recall_at_10": 0.958, "recall_at_20": 0.974, "recall_at_50": 0.994, "recall_at_100": 0.998, "precision_at_1": 0.842, "precision_at_3": 0.30333, "precision_at_5": 0.1852, "precision_at_10": 0.0958, "precision_at_20": 0.0487, "precision_at_50": 0.01988, "precision_at_100": 0.00998, "mrr_at_1": 0.846, "mrr_at_3": 0.8753333333333334, "mrr_at_5": 0.8791333333333333, "mrr_at_10": 0.883215873015873, "mrr_at_20": 0.8845011145287461, "mrr_at_50": 0.8851056968145472, "mrr_at_100": 0.8851712618465302, "naucs_at_1_max": 0.762746899402848, "naucs_at_1_std": -0.09687891842232711, "naucs_at_1_diff1": 0.93131510012539, "naucs_at_3_max": 0.7958190683680891, "naucs_at_3_std": -0.08053740014524166, "naucs_at_3_diff1": 0.9046581595601199, "naucs_at_5_max": 0.8209932621697326, "naucs_at_5_std": -0.06355515179044569, "naucs_at_5_diff1": 0.913632119514472, "naucs_at_10_max": 0.9291938997821336, "naucs_at_10_std": 0.06940553999377147, "naucs_at_10_diff1": 0.9618736383442255, "naucs_at_20_max": 0.9384112619406718, "naucs_at_20_std": 0.2580621992386671, "naucs_at_20_diff1": 0.9899446958270457, "naucs_at_50_max": 0.9564270152505304, "naucs_at_50_std": -0.061935885465295104, "naucs_at_50_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.85714, "ndcg_at_3": 0.90616, "ndcg_at_5": 0.91046, "ndcg_at_10": 0.91828, "ndcg_at_20": 0.92089, "ndcg_at_50": 0.92319, "ndcg_at_100": 0.92382, "map_at_1": 0.85714, "map_at_3": 0.89464, "map_at_5": 0.89696, "map_at_10": 0.90003, "map_at_20": 0.90069, "map_at_50": 0.90113, "map_at_100": 0.9012, "recall_at_1": 0.85714, "recall_at_3": 0.93929, "recall_at_5": 0.95, "recall_at_10": 0.975, "recall_at_20": 0.98571, "recall_at_50": 0.99643, "recall_at_100": 1.0, "precision_at_1": 0.85714, "precision_at_3": 0.3131, "precision_at_5": 0.19, "precision_at_10": 0.0975, "precision_at_20": 0.04929, "precision_at_50": 0.01993, "precision_at_100": 0.01, "mrr_at_1": 0.8571428571428571, "mrr_at_3": 0.8946428571428572, "mrr_at_5": 0.89625, "mrr_at_10": 0.8999489795918367, "mrr_at_20": 0.9006087018140589, "mrr_at_50": 0.9010484076109075, "mrr_at_100": 0.9011170889295889, "naucs_at_1_max": 0.5042274052478143, "naucs_at_1_std": 0.15470116618076035, "naucs_at_1_diff1": 0.8651239067055385, "naucs_at_3_max": 0.6153127917833795, "naucs_at_3_std": 0.4349426044927801, "naucs_at_3_diff1": 0.7869500741473071, "naucs_at_5_max": 0.5725623582766437, "naucs_at_5_std": 0.4422102174203035, "naucs_at_5_diff1": 0.7964852607709757, "naucs_at_10_max": 0.4158329998666156, "naucs_at_10_std": 0.32713085234094164, "naucs_at_10_diff1": 0.6116446578631451, "naucs_at_20_max": 0.24964985994398026, "naucs_at_20_std": 0.21288515406162958, "naucs_at_20_diff1": 0.6785714285714314, "naucs_at_50_max": 0.8692810457515607, "naucs_at_50_std": 0.8692810457515607, "naucs_at_50_diff1": 0.7222222222221809, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0}, "tatdqa": {"ndcg_at_1": 0.69934, "ndcg_at_3": 0.79233, "ndcg_at_5": 0.81055, "ndcg_at_10": 0.82355, "ndcg_at_20": 0.82931, "ndcg_at_50": 0.83237, "ndcg_at_100": 0.83391, "map_at_1": 0.69934, "map_at_3": 0.76959, "map_at_5": 0.77979, "map_at_10": 0.78535, "map_at_20": 0.78692, "map_at_50": 0.78745, "map_at_100": 0.78758, "recall_at_1": 0.69934, "recall_at_3": 0.85809, "recall_at_5": 0.90198, "recall_at_10": 0.94107, "recall_at_20": 0.96392, "recall_at_50": 0.97895, "recall_at_100": 0.98857, "precision_at_1": 0.69934, "precision_at_3": 0.28603, "precision_at_5": 0.1804, "precision_at_10": 0.09411, "precision_at_20": 0.0482, "precision_at_50": 0.01958, "precision_at_100": 0.00989, "mrr_at_1": 0.6945279615153337, "mrr_at_3": 0.7672880336740829, "mrr_at_5": 0.7785628382441371, "mrr_at_10": 0.7839064990598364, "mrr_at_20": 0.7854265248894812, "mrr_at_50": 0.7860095907963216, "mrr_at_100": 0.7861276188247445, "naucs_at_1_max": 0.22893544807358054, "naucs_at_1_std": -0.10645073148522476, "naucs_at_1_diff1": 0.820977721729132, "naucs_at_3_max": 0.36359547295706673, "naucs_at_3_std": 0.04589921689064907, "naucs_at_3_diff1": 0.7721105105285038, "naucs_at_5_max": 0.38687174851887957, "naucs_at_5_std": 0.13613442362048297, "naucs_at_5_diff1": 0.7514418550740282, "naucs_at_10_max": 0.515265589904788, "naucs_at_10_std": 0.41696526710652737, "naucs_at_10_diff1": 0.7441091180365171, "naucs_at_20_max": 0.5145946804670753, "naucs_at_20_std": 0.46286538260906074, "naucs_at_20_diff1": 0.7308007486507647, "naucs_at_50_max": 0.6663489691190478, "naucs_at_50_std": 0.6527939062776273, "naucs_at_50_diff1": 0.7597957531590336, "naucs_at_100_max": 0.6806290990559558, "naucs_at_100_std": 0.7236588802071027, "naucs_at_100_diff1": 0.7904400313210926}, "shift_project": {"ndcg_at_1": 0.8, "ndcg_at_3": 0.8844, "ndcg_at_5": 0.89258, "ndcg_at_10": 0.89915, "ndcg_at_20": 0.90194, "ndcg_at_50": 0.90398, "ndcg_at_100": 0.90398, "map_at_1": 0.8, "map_at_3": 0.865, "map_at_5": 0.8695, "map_at_10": 0.87228, "map_at_20": 0.87319, "map_at_50": 0.87353, "map_at_100": 0.87353, "recall_at_1": 0.8, "recall_at_3": 0.94, "recall_at_5": 0.96, "recall_at_10": 0.98, "recall_at_20": 0.99, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.8, "precision_at_3": 0.31333, "precision_at_5": 0.192, "precision_at_10": 0.098, "precision_at_20": 0.0495, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.79, "mrr_at_3": 0.8633333333333333, "mrr_at_5": 0.8658333333333332, "mrr_at_10": 0.8686111111111111, "mrr_at_20": 0.8695202020202021, "mrr_at_50": 0.869920202020202, "mrr_at_100": 0.869920202020202, "naucs_at_1_max": 0.023051948051947945, "naucs_at_1_std": -0.4089660339660347, "naucs_at_1_diff1": 0.7242257742257738, "naucs_at_3_max": 0.18285091814503548, "naucs_at_3_std": -0.27653283535636064, "naucs_at_3_diff1": 0.6640211640211647, "naucs_at_5_max": -0.1562791783379993, "naucs_at_5_std": -0.6954948646125065, "naucs_at_5_diff1": 0.9346405228758139, "naucs_at_10_max": -0.43534080298785716, "naucs_at_10_std": -0.43534080298785716, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": -1.7399626517273863, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_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 sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
|
3 |
+
size 11420371
|
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 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
config:
|
2 |
+
(): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
|
3 |
+
output_dir: !path ../../../models/colqwen2-ba256-ckpt-3e
|
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 |
+
# 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
|
14 |
+
pretrained_model_name_or_path: "./models/colqwen2_base"
|
15 |
+
torch_dtype: !ext torch.bfloat16
|
16 |
+
use_cache: false
|
17 |
+
attn_implementation: "flash_attention_2"
|
18 |
+
# device_map: "auto"
|
19 |
+
# quantization_config:
|
20 |
+
# (): transformers.BitsAndBytesConfig
|
21 |
+
# load_in_4bit: true
|
22 |
+
# bnb_4bit_quant_type: "nf4"
|
23 |
+
# bnb_4bit_compute_dtype: "bfloat16"
|
24 |
+
# bnb_4bit_use_double_quant: true
|
25 |
+
|
26 |
+
dataset_loading_func: !ext colpali_engine.utils.dataset_transformation.load_train_set
|
27 |
+
eval_dataset_loader: !import ../data/test_data.yaml
|
28 |
+
|
29 |
+
# max_length: 50
|
30 |
+
run_eval: true
|
31 |
+
add_suffix: 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: 4
|
45 |
+
per_device_eval_batch_size: 8
|
46 |
+
eval_strategy: "steps"
|
47 |
+
dataloader_num_workers: 8
|
48 |
+
# bf16: true
|
49 |
+
save_steps: 500
|
50 |
+
logging_steps: 10
|
51 |
+
eval_steps: 100
|
52 |
+
warmup_steps: 50
|
53 |
+
learning_rate: 5e-4
|
54 |
+
save_total_limit: 1
|
55 |
+
# resume_from_checkpoint: true
|
56 |
+
# optim: "paged_adamw_8bit"
|
57 |
+
# wandb logging
|
58 |
+
# wandb_project: "colqwen2"
|
59 |
+
# run_name: "colqwen2-ba32-nolora"
|
60 |
+
report_to: "wandb"
|
61 |
+
|
62 |
+
|
63 |
+
peft_config:
|
64 |
+
(): peft.LoraConfig
|
65 |
+
r: 32
|
66 |
+
lora_alpha: 32
|
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
|
|