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 +72 -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/colqwen2-7b-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/colqwen2-7b-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 sha256:0fe76a13585e8fc55b5258b10b3f9fe471aba5d4a90eb5bc523466f1d63c3b3c
|
3 |
+
size 161771384
|
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 |
+
55fff065385c1f6a868497edd2db5db088d9c3e0
|
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": 0.826, "ndcg_at_3": 0.88395, "ndcg_at_5": 0.89135, "ndcg_at_10": 0.89712, "ndcg_at_20": 0.90009, "ndcg_at_50": 0.90242, "ndcg_at_100": 0.90369, "map_at_1": 0.826, "map_at_3": 0.87067, "map_at_5": 0.87477, "map_at_10": 0.87712, "map_at_20": 0.8779, "map_at_50": 0.87825, "map_at_100": 0.87836, "recall_at_1": 0.826, "recall_at_3": 0.922, "recall_at_5": 0.94, "recall_at_10": 0.958, "recall_at_20": 0.97, "recall_at_50": 0.982, "recall_at_100": 0.99, "precision_at_1": 0.826, "precision_at_3": 0.30733, "precision_at_5": 0.188, "precision_at_10": 0.0958, "precision_at_20": 0.0485, "precision_at_50": 0.01964, "precision_at_100": 0.0099, "mrr_at_1": 0.828, "mrr_at_3": 0.869, "mrr_at_5": 0.8742000000000001, "mrr_at_10": 0.8767158730158731, "mrr_at_20": 0.8776762126762127, "mrr_at_50": 0.878013022025774, "mrr_at_100": 0.8781584051922459, "naucs_at_1_max": 0.3432503380797081, "naucs_at_1_std": 0.2095241883246028, "naucs_at_1_diff1": 0.9486630226030438, "naucs_at_3_max": 0.4193540664128913, "naucs_at_3_std": 0.6719935837582925, "naucs_at_3_diff1": 0.9475089180971545, "naucs_at_5_max": 0.4053065670712697, "naucs_at_5_std": 0.7934484905073144, "naucs_at_5_diff1": 0.9540927482103968, "naucs_at_10_max": 0.4086078875994817, "naucs_at_10_std": 0.8241741140900799, "naucs_at_10_diff1": 0.9751011515717399, "naucs_at_20_max": 0.3347650171179612, "naucs_at_20_std": 0.8932461873638364, "naucs_at_20_diff1": 0.9738562091503296, "naucs_at_50_max": 0.3245668637825497, "naucs_at_50_std": 0.865649963689171, "naucs_at_50_diff1": 0.9854756717501884, "naucs_at_100_max": 0.6406162464985967, "naucs_at_100_std": 0.8398692810457434, "naucs_at_100_diff1": 0.9738562091503188}, "syntheticDocQA_energy": {"ndcg_at_1": 0.95, "ndcg_at_3": 0.96762, "ndcg_at_5": 0.96762, "ndcg_at_10": 0.96762, "ndcg_at_20": 0.96762, "ndcg_at_50": 0.97149, "ndcg_at_100": 0.97149, "map_at_1": 0.95, "map_at_3": 0.96333, "map_at_5": 0.96333, "map_at_10": 0.96333, "map_at_20": 0.96333, "map_at_50": 0.96391, "map_at_100": 0.96391, "recall_at_1": 0.95, "recall_at_3": 0.98, "recall_at_5": 0.98, "recall_at_10": 0.98, "recall_at_20": 0.98, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.95, "precision_at_3": 0.32667, "precision_at_5": 0.196, "precision_at_10": 0.098, "precision_at_20": 0.049, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.97, "mrr_at_3": 0.975, "mrr_at_5": 0.975, "mrr_at_10": 0.975, "mrr_at_20": 0.975, "mrr_at_50": 0.9755887445887446, "mrr_at_100": 0.9755887445887446, "naucs_at_1_max": 0.02399626517273991, "naucs_at_1_std": -0.8497665732959815, "naucs_at_1_diff1": 0.9738562091503253, "naucs_at_3_max": 0.9346405228758099, "naucs_at_3_std": 0.19140989729224936, "naucs_at_3_diff1": 0.9346405228758099, "naucs_at_5_max": 0.9346405228758136, "naucs_at_5_std": 0.1914098972922579, "naucs_at_5_diff1": 0.9346405228758136, "naucs_at_10_max": 0.9346405228758136, "naucs_at_10_std": 0.1914098972922579, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 0.9346405228758136, "naucs_at_20_std": 0.1914098972922579, "naucs_at_20_diff1": 0.9346405228758136, "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": 0.4025443510737659, "naucs_at_1_std": 0.29470121381886283, "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": 0.96, "ndcg_at_3": 0.97893, "ndcg_at_5": 0.98323, "ndcg_at_10": 0.98323, "ndcg_at_20": 0.98323, "ndcg_at_50": 0.98323, "ndcg_at_100": 0.98323, "map_at_1": 0.96, "map_at_3": 0.975, "map_at_5": 0.9775, "map_at_10": 0.9775, "map_at_20": 0.9775, "map_at_50": 0.9775, "map_at_100": 0.9775, "recall_at_1": 0.96, "recall_at_3": 0.99, "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": 0.33, "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": 0.975, "mrr_at_5": 0.9775, "mrr_at_10": 0.9775, "mrr_at_20": 0.9775, "mrr_at_50": 0.9775, "mrr_at_100": 0.9775, "naucs_at_1_max": 0.6458916900093364, "naucs_at_1_std": -0.053688141923436454, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 0.8692810457516356, "naucs_at_3_std": -1.1517273576097802, "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": 0.87, "ndcg_at_3": 0.93678, "ndcg_at_5": 0.94452, "ndcg_at_10": 0.94452, "ndcg_at_20": 0.94452, "ndcg_at_50": 0.94452, "ndcg_at_100": 0.94452, "map_at_1": 0.87, "map_at_3": 0.92167, "map_at_5": 0.92567, "map_at_10": 0.92567, "map_at_20": 0.92567, "map_at_50": 0.92567, "map_at_100": 0.92567, "recall_at_1": 0.87, "recall_at_3": 0.98, "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": 0.87, "precision_at_3": 0.32667, "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": 0.88, "mrr_at_3": 0.9283333333333332, "mrr_at_5": 0.9323333333333333, "mrr_at_10": 0.9323333333333333, "mrr_at_20": 0.9323333333333333, "mrr_at_50": 0.9323333333333333, "mrr_at_100": 0.9323333333333333, "naucs_at_1_max": 0.37621269347552294, "naucs_at_1_std": 0.36136414130193245, "naucs_at_1_diff1": 0.8826186773309634, "naucs_at_3_max": 0.6136788048552655, "naucs_at_3_std": 0.6136788048552655, "naucs_at_3_diff1": 0.7117180205415458, "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}, "infovqa_subsampled": {"ndcg_at_1": 0.878, "ndcg_at_3": 0.90088, "ndcg_at_5": 0.91414, "ndcg_at_10": 0.91797, "ndcg_at_20": 0.91957, "ndcg_at_50": 0.92115, "ndcg_at_100": 0.92343, "map_at_1": 0.878, "map_at_3": 0.895, "map_at_5": 0.9024, "map_at_10": 0.90396, "map_at_20": 0.90444, "map_at_50": 0.90469, "map_at_100": 0.9049, "recall_at_1": 0.878, "recall_at_3": 0.918, "recall_at_5": 0.95, "recall_at_10": 0.962, "recall_at_20": 0.968, "recall_at_50": 0.976, "recall_at_100": 0.99, "precision_at_1": 0.878, "precision_at_3": 0.306, "precision_at_5": 0.19, "precision_at_10": 0.0962, "precision_at_20": 0.0484, "precision_at_50": 0.01952, "precision_at_100": 0.0099, "mrr_at_1": 0.874, "mrr_at_3": 0.8923333333333334, "mrr_at_5": 0.9007333333333334, "mrr_at_10": 0.9020444444444444, "mrr_at_20": 0.9025257278669044, "mrr_at_50": 0.9028050383312147, "mrr_at_100": 0.9029730583888165, "naucs_at_1_max": 0.6417911617626315, "naucs_at_1_std": -0.011788496809894352, "naucs_at_1_diff1": 0.9438792306124684, "naucs_at_3_max": 0.7491858532030709, "naucs_at_3_std": 0.04282526018537632, "naucs_at_3_diff1": 0.9373163899706234, "naucs_at_5_max": 0.8344724556489264, "naucs_at_5_std": 0.2926610644257683, "naucs_at_5_diff1": 0.9470588235294107, "naucs_at_10_max": 0.9240748931151417, "naucs_at_10_std": 0.578775369797045, "naucs_at_10_diff1": 0.9587203302373579, "naucs_at_20_max": 0.9180088702147511, "naucs_at_20_std": 0.5161356209150314, "naucs_at_20_diff1": 0.9591503267973829, "naucs_at_50_max": 0.9015717398070241, "naucs_at_50_std": 0.5081310301898541, "naucs_at_50_diff1": 0.9673202614379068, "naucs_at_100_max": 0.8921568627450854, "naucs_at_100_std": 0.6873015873015698, "naucs_at_100_diff1": 0.9738562091503188}, "docvqa_subsampled": {"ndcg_at_1": 0.472, "ndcg_at_3": 0.54143, "ndcg_at_5": 0.55975, "ndcg_at_10": 0.57821, "ndcg_at_20": 0.59145, "ndcg_at_50": 0.60588, "ndcg_at_100": 0.61495, "map_at_1": 0.472, "map_at_3": 0.524, "map_at_5": 0.5338, "map_at_10": 0.54163, "map_at_20": 0.54531, "map_at_50": 0.54753, "map_at_100": 0.54833, "recall_at_1": 0.472, "recall_at_3": 0.592, "recall_at_5": 0.638, "recall_at_10": 0.694, "recall_at_20": 0.746, "recall_at_50": 0.82, "recall_at_100": 0.876, "precision_at_1": 0.472, "precision_at_3": 0.19733, "precision_at_5": 0.1276, "precision_at_10": 0.0694, "precision_at_20": 0.0373, "precision_at_50": 0.0164, "precision_at_100": 0.00876, "mrr_at_1": 0.478, "mrr_at_3": 0.5263333333333333, "mrr_at_5": 0.5356333333333333, "mrr_at_10": 0.5434126984126985, "mrr_at_20": 0.5472397111058875, "mrr_at_50": 0.5499635119629092, "mrr_at_100": 0.5505736042826437, "naucs_at_1_max": 0.3923025767156111, "naucs_at_1_std": 0.7053772180760662, "naucs_at_1_diff1": 0.9042387552384067, "naucs_at_3_max": 0.29406297063253023, "naucs_at_3_std": 0.759083207831325, "naucs_at_3_diff1": 0.8269248870481934, "naucs_at_5_max": 0.22360003435693662, "naucs_at_5_std": 0.8072734907602107, "naucs_at_5_diff1": 0.8233417210916594, "naucs_at_10_max": 0.158478323509218, "naucs_at_10_std": 0.8277726591986796, "naucs_at_10_diff1": 0.7939532782424016, "naucs_at_20_max": 0.06102847885472823, "naucs_at_20_std": 0.8541052779488288, "naucs_at_20_diff1": 0.7847864809128443, "naucs_at_50_max": 0.04328119836986498, "naucs_at_50_std": 0.89758233285604, "naucs_at_50_diff1": 0.7738242097147262, "naucs_at_100_max": 0.015149408238311582, "naucs_at_100_std": 0.9025215537220722, "naucs_at_100_diff1": 0.789476530391521}, "arxivqa_subsampled": {"ndcg_at_1": 0.822, "ndcg_at_3": 0.87355, "ndcg_at_5": 0.88413, "ndcg_at_10": 0.89092, "ndcg_at_20": 0.89665, "ndcg_at_50": 0.89867, "ndcg_at_100": 0.89967, "map_at_1": 0.822, "map_at_3": 0.86033, "map_at_5": 0.86613, "map_at_10": 0.86912, "map_at_20": 0.87078, "map_at_50": 0.87112, "map_at_100": 0.87122, "recall_at_1": 0.822, "recall_at_3": 0.912, "recall_at_5": 0.938, "recall_at_10": 0.958, "recall_at_20": 0.98, "recall_at_50": 0.99, "recall_at_100": 0.996, "precision_at_1": 0.822, "precision_at_3": 0.304, "precision_at_5": 0.1876, "precision_at_10": 0.0958, "precision_at_20": 0.049, "precision_at_50": 0.0198, "precision_at_100": 0.00996, "mrr_at_1": 0.822, "mrr_at_3": 0.8613333333333334, "mrr_at_5": 0.8663333333333334, "mrr_at_10": 0.8695214285714286, "mrr_at_20": 0.8711353662677191, "mrr_at_50": 0.8715260011883541, "mrr_at_100": 0.8715838702010618, "naucs_at_1_max": 0.7184700475188902, "naucs_at_1_std": -0.08461589824057751, "naucs_at_1_diff1": 0.942910559877141, "naucs_at_3_max": 0.7786796536796564, "naucs_at_3_std": -0.022472625413802825, "naucs_at_3_diff1": 0.9324123588829496, "naucs_at_5_max": 0.7821451161109595, "naucs_at_5_std": -0.10835517002500032, "naucs_at_5_diff1": 0.9530887623866757, "naucs_at_10_max": 0.7989862611711338, "naucs_at_10_std": -0.19698990707394395, "naucs_at_10_diff1": 0.9502023031434798, "naucs_at_20_max": 0.7794584500466787, "naucs_at_20_std": -0.047385620915033094, "naucs_at_20_diff1": 0.934640522875813, "naucs_at_50_max": 0.947712418300658, "naucs_at_50_std": -0.15378151260503836, "naucs_at_50_diff1": 0.9738562091503188, "naucs_at_100_max": 0.9346405228758466, "naucs_at_100_std": -0.3699813258636757, "naucs_at_100_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.83214, "ndcg_at_3": 0.86849, "ndcg_at_5": 0.88218, "ndcg_at_10": 0.89148, "ndcg_at_20": 0.89908, "ndcg_at_50": 0.90177, "ndcg_at_100": 0.90177, "map_at_1": 0.83214, "map_at_3": 0.85893, "map_at_5": 0.86679, "map_at_10": 0.87065, "map_at_20": 0.87294, "map_at_50": 0.87331, "map_at_100": 0.87331, "recall_at_1": 0.83214, "recall_at_3": 0.89643, "recall_at_5": 0.92857, "recall_at_10": 0.95714, "recall_at_20": 0.98571, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.83214, "precision_at_3": 0.29881, "precision_at_5": 0.18571, "precision_at_10": 0.09571, "precision_at_20": 0.04929, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.8357142857142857, "mrr_at_3": 0.8601190476190477, "mrr_at_5": 0.8690476190476191, "mrr_at_10": 0.872640306122449, "mrr_at_20": 0.8752497021535887, "mrr_at_50": 0.8756202568795441, "mrr_at_100": 0.8756202568795441, "naucs_at_1_max": 0.48693290265746514, "naucs_at_1_std": 0.2166243681439694, "naucs_at_1_diff1": 0.873135893617467, "naucs_at_3_max": 0.5662052459652638, "naucs_at_3_std": 0.4133380769106388, "naucs_at_3_diff1": 0.8562534363983321, "naucs_at_5_max": 0.6014005602240904, "naucs_at_5_std": 0.41097105508870374, "naucs_at_5_diff1": 0.8548319327731102, "naucs_at_10_max": 0.6419623404917498, "naucs_at_10_std": 0.33916900093370245, "naucs_at_10_diff1": 0.8869825708061017, "naucs_at_20_max": 0.865196078431377, "naucs_at_20_std": 0.7496498599439745, "naucs_at_20_diff1": 0.8978758169934754, "naucs_at_50_max": 1.0, "naucs_at_50_std": 1.0, "naucs_at_50_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0}, "tatdqa": {"ndcg_at_1": 0.66627, "ndcg_at_3": 0.76591, "ndcg_at_5": 0.78897, "ndcg_at_10": 0.80301, "ndcg_at_20": 0.80898, "ndcg_at_50": 0.81233, "ndcg_at_100": 0.81417, "map_at_1": 0.66627, "map_at_3": 0.74243, "map_at_5": 0.75524, "map_at_10": 0.76106, "map_at_20": 0.7628, "map_at_50": 0.76334, "map_at_100": 0.7635, "recall_at_1": 0.66627, "recall_at_3": 0.83343, "recall_at_5": 0.88936, "recall_at_10": 0.93265, "recall_at_20": 0.9555, "recall_at_50": 0.97234, "recall_at_100": 0.98376, "precision_at_1": 0.66627, "precision_at_3": 0.27781, "precision_at_5": 0.17787, "precision_at_10": 0.09327, "precision_at_20": 0.04778, "precision_at_50": 0.01945, "precision_at_100": 0.00984, "mrr_at_1": 0.6650631389055923, "mrr_at_3": 0.7424333533774304, "mrr_at_5": 0.7541290839847664, "mrr_at_10": 0.7603403678569043, "mrr_at_20": 0.7620416242709359, "mrr_at_50": 0.7625731305022777, "mrr_at_100": 0.7627555296002397, "naucs_at_1_max": 0.2255901193553477, "naucs_at_1_std": -0.17195994632386122, "naucs_at_1_diff1": 0.8184172224887907, "naucs_at_3_max": 0.2738703807942716, "naucs_at_3_std": -0.11962815389024864, "naucs_at_3_diff1": 0.7412672113098526, "naucs_at_5_max": 0.3481139472219308, "naucs_at_5_std": -0.026753182766958084, "naucs_at_5_diff1": 0.703118215452914, "naucs_at_10_max": 0.4767078473369491, "naucs_at_10_std": 0.2645481592876129, "naucs_at_10_diff1": 0.6929624809523717, "naucs_at_20_max": 0.5055479453630981, "naucs_at_20_std": 0.42820219435749896, "naucs_at_20_diff1": 0.6905113082549136, "naucs_at_50_max": 0.5175966319812615, "naucs_at_50_std": 0.518633493957509, "naucs_at_50_diff1": 0.6885449373033483, "naucs_at_100_max": 0.6300622311883954, "naucs_at_100_std": 0.7252919027287567, "naucs_at_100_diff1": 0.7003719897704582}, "shift_project": {"ndcg_at_1": 0.7, "ndcg_at_3": 0.82702, "ndcg_at_5": 0.8352, "ndcg_at_10": 0.84124, "ndcg_at_20": 0.84639, "ndcg_at_50": 0.84836, "ndcg_at_100": 0.84996, "map_at_1": 0.7, "map_at_3": 0.795, "map_at_5": 0.7995, "map_at_10": 0.80175, "map_at_20": 0.80321, "map_at_50": 0.80351, "map_at_100": 0.80365, "recall_at_1": 0.7, "recall_at_3": 0.92, "recall_at_5": 0.94, "recall_at_10": 0.96, "recall_at_20": 0.98, "recall_at_50": 0.99, "recall_at_100": 1.0, "precision_at_1": 0.7, "precision_at_3": 0.30667, "precision_at_5": 0.188, "precision_at_10": 0.096, "precision_at_20": 0.049, "precision_at_50": 0.0198, "precision_at_100": 0.01, "mrr_at_1": 0.7, "mrr_at_3": 0.795, "mrr_at_5": 0.7995, "mrr_at_10": 0.8029999999999999, "mrr_at_20": 0.8036249999999999, "mrr_at_50": 0.8039475806451613, "mrr_at_100": 0.8040827157802964, "naucs_at_1_max": 0.007692307692307685, "naucs_at_1_std": -0.21826697892271701, "naucs_at_1_diff1": 0.6957665285534135, "naucs_at_3_max": 0.2762605042016824, "naucs_at_3_std": -0.2441059757236238, "naucs_at_3_diff1": 0.8978758169934661, "naucs_at_5_max": 0.15561780267662587, "naucs_at_5_std": -0.31738250855898026, "naucs_at_5_diff1": 0.8856209150326813, "naucs_at_10_max": -0.04726890756302253, "naucs_at_10_std": -0.6832399626517155, "naucs_at_10_diff1": 0.9305555555555542, "naucs_at_20_max": -0.5088702147525547, "naucs_at_20_std": -0.5088702147525547, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": 0.7222222222222041, "naucs_at_50_std": 0.7222222222222041, "naucs_at_50_diff1": 1.0, "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 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
config:
|
2 |
+
(): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
|
3 |
+
output_dir: !path ../../../models/colqwen2-7b
|
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/colqwen2-7b-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/colqwen2-7b-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 |
+
loss_func:
|
32 |
+
(): colpali_engine.loss.late_interaction_losses.ColbertPairwiseCELoss
|
33 |
+
tr_args:
|
34 |
+
(): transformers.training_args.TrainingArguments
|
35 |
+
output_dir: null
|
36 |
+
overwrite_output_dir: true
|
37 |
+
num_train_epochs: 1
|
38 |
+
per_device_train_batch_size: 16
|
39 |
+
gradient_checkpointing: true
|
40 |
+
gradient_checkpointing_kwargs: { "use_reentrant": false }
|
41 |
+
# gradient_checkpointing: true
|
42 |
+
# 6 x 8 gpus = 48 batch size
|
43 |
+
# gradient_accumulation_steps: 4
|
44 |
+
per_device_eval_batch_size: 16
|
45 |
+
eval_strategy: "steps"
|
46 |
+
dataloader_num_workers: 8
|
47 |
+
# bf16: true
|
48 |
+
save_steps: 500
|
49 |
+
logging_steps: 10
|
50 |
+
eval_steps: 100
|
51 |
+
warmup_steps: 100
|
52 |
+
learning_rate: 5e-5
|
53 |
+
save_total_limit: 1
|
54 |
+
# resume_from_checkpoint: true
|
55 |
+
# optim: "paged_adamw_8bit"
|
56 |
+
# wandb logging
|
57 |
+
# wandb_project: "colqwen2"
|
58 |
+
# run_name: "colqwen2-ba32-nolora"
|
59 |
+
report_to: "wandb"
|
60 |
+
|
61 |
+
|
62 |
+
peft_config:
|
63 |
+
(): peft.LoraConfig
|
64 |
+
r: 32
|
65 |
+
lora_alpha: 32
|
66 |
+
lora_dropout: 0.1
|
67 |
+
init_lora_weights: "gaussian"
|
68 |
+
bias: "none"
|
69 |
+
task_type: "FEATURE_EXTRACTION"
|
70 |
+
target_modules: '(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
|
71 |
+
# target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
|
72 |
+
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|