Upload folder using huggingface_hub
Browse files- 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 +0 -0
- tokenizer_config.json +144 -0
- training_config.yml +63 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: vidore/colqwen2-base
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.11.1
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "vidore/colqwen2-base",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": "gaussian",
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
|
23 |
+
"task_type": "FEATURE_EXTRACTION",
|
24 |
+
"use_dora": false,
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49f197f2601d0136d0af935a8da98b4409bc7ed82f33d5527a870a5c21a0abe0
|
3 |
+
size 74018232
|
added_tokens.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|box_end|>": 151649,
|
3 |
+
"<|box_start|>": 151648,
|
4 |
+
"<|endoftext|>": 151643,
|
5 |
+
"<|im_end|>": 151645,
|
6 |
+
"<|im_start|>": 151644,
|
7 |
+
"<|image_pad|>": 151655,
|
8 |
+
"<|object_ref_end|>": 151647,
|
9 |
+
"<|object_ref_start|>": 151646,
|
10 |
+
"<|quad_end|>": 151651,
|
11 |
+
"<|quad_start|>": 151650,
|
12 |
+
"<|video_pad|>": 151656,
|
13 |
+
"<|vision_end|>": 151653,
|
14 |
+
"<|vision_pad|>": 151654,
|
15 |
+
"<|vision_start|>": 151652
|
16 |
+
}
|
chat_template.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
3 |
+
}
|
git_hash.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
3ec85f462475d4564d0926a885fc5fe1b95e606d
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": true,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.48145466,
|
8 |
+
0.4578275,
|
9 |
+
0.40821073
|
10 |
+
],
|
11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.26862954,
|
14 |
+
0.26130258,
|
15 |
+
0.27577711
|
16 |
+
],
|
17 |
+
"max_pixels": 12845056,
|
18 |
+
"merge_size": 2,
|
19 |
+
"min_pixels": 3136,
|
20 |
+
"patch_size": 14,
|
21 |
+
"processor_class": "ColQwen2Processor",
|
22 |
+
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"max_pixels": 12845056,
|
26 |
+
"min_pixels": 3136
|
27 |
+
},
|
28 |
+
"temporal_patch_size": 2
|
29 |
+
}
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"validation_set": {"ndcg_at_1": 0.816, "ndcg_at_3": 0.87743, "ndcg_at_5": 0.88801, "ndcg_at_10": 0.89049, "ndcg_at_20": 0.89308, "ndcg_at_100": 0.8984, "ndcg_at_1000": 0.89954, "map_at_1": 0.816, "map_at_3": 0.86267, "map_at_5": 0.86847, "map_at_10": 0.86942, "map_at_20": 0.87018, "map_at_100": 0.87095, "map_at_1000": 0.87101, "recall_at_1": 0.816, "recall_at_3": 0.92, "recall_at_5": 0.946, "recall_at_10": 0.954, "recall_at_20": 0.964, "recall_at_100": 0.992, "recall_at_1000": 1.0, "precision_at_1": 0.816, "precision_at_3": 0.30667, "precision_at_5": 0.1892, "precision_at_10": 0.0954, "precision_at_20": 0.0482, "precision_at_100": 0.00992, "precision_at_1000": 0.001, "mrr_at_1": 0.82, "mrr_at_3": 0.8629999999999998, "mrr_at_5": 0.8703999999999998, "mrr_at_10": 0.8713301587301585, "mrr_at_20": 0.8723493506493503, "mrr_at_100": 0.8731067876052313, "mrr_at_1000": 0.8731343731583642, "naucs_at_1_max": 0.4089927902257919, "naucs_at_1_std": -0.3392695246729696, "naucs_at_1_diff1": 0.9499201312437934, "naucs_at_3_max": 0.5994747899159686, "naucs_at_3_std": -0.13678804855275456, "naucs_at_3_diff1": 0.9297385620915034, "naucs_at_5_max": 0.6925338036449152, "naucs_at_5_std": 0.06575716706435682, "naucs_at_5_diff1": 0.9552166545630597, "naucs_at_10_max": 0.7244955953395846, "naucs_at_10_std": 0.18962367555717077, "naucs_at_10_diff1": 0.9595055413469742, "naucs_at_20_max": 0.6799979250959618, "naucs_at_20_std": 0.15966386554621653, "naucs_at_20_diff1": 0.9700435729847436, "naucs_at_100_max": 0.5180905695611601, "naucs_at_100_std": 0.23342670401492077, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_energy": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.94786, "ndcg_at_5": 0.94786, "ndcg_at_10": 0.95101, "ndcg_at_20": 0.9538, "ndcg_at_100": 0.95601, "ndcg_at_1000": 0.95601, "map_at_1": 0.91, "map_at_3": 0.94, "map_at_5": 0.94, "map_at_10": 0.94125, "map_at_20": 0.94216, "map_at_100": 0.94261, "map_at_1000": 0.94261, "recall_at_1": 0.91, "recall_at_3": 0.97, "recall_at_5": 0.97, "recall_at_10": 0.98, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.91, "precision_at_3": 0.32333, "precision_at_5": 0.194, "precision_at_10": 0.098, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.94, "mrr_at_3": 0.955, "mrr_at_5": 0.955, "mrr_at_10": 0.9564285714285714, "mrr_at_20": 0.9573376623376624, "mrr_at_100": 0.9577922077922078, "mrr_at_1000": 0.9577922077922078, "naucs_at_1_max": 0.2695300342359169, "naucs_at_1_std": -0.6963896669779026, "naucs_at_1_diff1": 0.9854756717501807, "naucs_at_3_max": 0.5714285714285686, "naucs_at_3_std": -1.21708683473389, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 0.5714285714285722, "naucs_at_5_std": -1.2170868347338937, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 0.7957516339869297, "naucs_at_10_std": -0.9556489262371616, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 0.7222222222222276, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.96655, "ndcg_at_5": 0.96655, "ndcg_at_10": 0.96655, "ndcg_at_20": 0.96655, "ndcg_at_100": 0.96655, "ndcg_at_1000": 0.96655, "map_at_1": 0.92, "map_at_3": 0.955, "map_at_5": 0.955, "map_at_10": 0.955, "map_at_20": 0.955, "map_at_100": 0.955, "map_at_1000": 0.955, "recall_at_1": 0.92, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.94, "mrr_at_3": 0.965, "mrr_at_5": 0.965, "mrr_at_10": 0.965, "mrr_at_20": 0.965, "mrr_at_100": 0.965, "mrr_at_1000": 0.965, "naucs_at_1_max": 0.7619047619047616, "naucs_at_1_std": -0.1527777777777763, "naucs_at_1_diff1": 0.9673202614379083, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.98, "ndcg_at_3": 0.98631, "ndcg_at_5": 0.99062, "ndcg_at_10": 0.99062, "ndcg_at_20": 0.99062, "ndcg_at_100": 0.99062, "ndcg_at_1000": 0.99062, "map_at_1": 0.98, "map_at_3": 0.985, "map_at_5": 0.9875, "map_at_10": 0.9875, "map_at_20": 0.9875, "map_at_100": 0.9875, "map_at_1000": 0.9875, "recall_at_1": 0.98, "recall_at_3": 0.99, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.98, "precision_at_3": 0.33, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.98, "mrr_at_3": 0.985, "mrr_at_5": 0.9875, "mrr_at_10": 0.9875, "mrr_at_20": 0.9875, "mrr_at_100": 0.9875, "mrr_at_1000": 0.9875, "naucs_at_1_max": 0.3489729225023353, "naucs_at_1_std": -0.808590102707748, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 0.8692810457516356, "naucs_at_3_std": 0.12278244631183229, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.85, "ndcg_at_3": 0.92309, "ndcg_at_5": 0.93171, "ndcg_at_10": 0.93472, "ndcg_at_20": 0.93472, "ndcg_at_100": 0.93472, "ndcg_at_1000": 0.93472, "map_at_1": 0.85, "map_at_3": 0.90667, "map_at_5": 0.91167, "map_at_10": 0.91278, "map_at_20": 0.91278, "map_at_100": 0.91278, "map_at_1000": 0.91278, "recall_at_1": 0.85, "recall_at_3": 0.97, "recall_at_5": 0.99, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.85, "precision_at_3": 0.32333, "precision_at_5": 0.198, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.86, "mrr_at_3": 0.9116666666666666, "mrr_at_5": 0.9166666666666665, "mrr_at_10": 0.9179166666666666, "mrr_at_20": 0.9179166666666666, "mrr_at_100": 0.9179166666666666, "mrr_at_1000": 0.9179166666666666, "naucs_at_1_max": 0.4882525219655072, "naucs_at_1_std": 0.2755938821998056, "naucs_at_1_diff1": 0.8752033843150019, "naucs_at_3_max": 0.8513849984438244, "naucs_at_3_std": 0.2376283846872095, "naucs_at_3_diff1": 0.9074074074074082, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.5541549953314738, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "infovqa_subsampled": {"ndcg_at_1": 0.856, "ndcg_at_3": 0.88802, "ndcg_at_5": 0.89964, "ndcg_at_10": 0.90561, "ndcg_at_20": 0.91178, "ndcg_at_100": 0.91336, "ndcg_at_1000": 0.91519, "map_at_1": 0.856, "map_at_3": 0.881, "map_at_5": 0.8875, "map_at_10": 0.89005, "map_at_20": 0.8918, "map_at_100": 0.89206, "map_at_1000": 0.89213, "recall_at_1": 0.856, "recall_at_3": 0.908, "recall_at_5": 0.936, "recall_at_10": 0.954, "recall_at_20": 0.978, "recall_at_100": 0.986, "recall_at_1000": 1.0, "precision_at_1": 0.856, "precision_at_3": 0.30267, "precision_at_5": 0.1872, "precision_at_10": 0.0954, "precision_at_20": 0.0489, "precision_at_100": 0.00986, "precision_at_1000": 0.001, "mrr_at_1": 0.86, "mrr_at_3": 0.8839999999999999, "mrr_at_5": 0.8895999999999998, "mrr_at_10": 0.8919190476190474, "mrr_at_20": 0.893826762736747, "mrr_at_100": 0.8940837133167153, "mrr_at_1000": 0.8941572107843205, "naucs_at_1_max": 0.6396625783444994, "naucs_at_1_std": -0.11759779554787107, "naucs_at_1_diff1": 0.9412753944240329, "naucs_at_3_max": 0.5607518369666695, "naucs_at_3_std": -0.23359923679616587, "naucs_at_3_diff1": 0.8989668331100549, "naucs_at_5_max": 0.7544496965452863, "naucs_at_5_std": -0.03478057889822458, "naucs_at_5_diff1": 0.9227503501400529, "naucs_at_10_max": 0.7531157390492416, "naucs_at_10_std": -0.19932610725450334, "naucs_at_10_diff1": 0.9488491048593367, "naucs_at_20_max": 0.9163907987437411, "naucs_at_20_std": 0.24034462269756168, "naucs_at_20_diff1": 0.9524658348187754, "naucs_at_100_max": 0.9603174603174626, "naucs_at_100_std": 0.28097905828998787, "naucs_at_100_diff1": 0.9626517273576126, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.462, "ndcg_at_3": 0.52421, "ndcg_at_5": 0.55269, "ndcg_at_10": 0.58165, "ndcg_at_20": 0.59442, "ndcg_at_100": 0.61615, "ndcg_at_1000": 0.62947, "map_at_1": 0.462, "map_at_3": 0.50967, "map_at_5": 0.52527, "map_at_10": 0.5375, "map_at_20": 0.54108, "map_at_100": 0.54388, "map_at_1000": 0.54434, "recall_at_1": 0.462, "recall_at_3": 0.566, "recall_at_5": 0.636, "recall_at_10": 0.724, "recall_at_20": 0.774, "recall_at_100": 0.894, "recall_at_1000": 1.0, "precision_at_1": 0.462, "precision_at_3": 0.18867, "precision_at_5": 0.1272, "precision_at_10": 0.0724, "precision_at_20": 0.0387, "precision_at_100": 0.00894, "precision_at_1000": 0.001, "mrr_at_1": 0.464, "mrr_at_3": 0.5140000000000001, "mrr_at_5": 0.5276, "mrr_at_10": 0.5392595238095239, "mrr_at_20": 0.5427890347354745, "mrr_at_100": 0.5456342789886727, "mrr_at_1000": 0.5461156386952566, "naucs_at_1_max": 0.6458196908851354, "naucs_at_1_std": 0.20323368757675922, "naucs_at_1_diff1": 0.8721936004754803, "naucs_at_3_max": 0.6349820968797422, "naucs_at_3_std": 0.26161988232234823, "naucs_at_3_diff1": 0.7944184557880087, "naucs_at_5_max": 0.6085398087052426, "naucs_at_5_std": 0.26688090665348296, "naucs_at_5_diff1": 0.7506481076524244, "naucs_at_10_max": 0.555114948298363, "naucs_at_10_std": 0.42525464696933346, "naucs_at_10_diff1": 0.7213517332983245, "naucs_at_20_max": 0.5278038772462562, "naucs_at_20_std": 0.5622415585240862, "naucs_at_20_diff1": 0.6966560907081347, "naucs_at_100_max": 0.557859893864365, "naucs_at_100_std": 0.9139733418525807, "naucs_at_100_diff1": 0.6317288749267865, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "arxivqa_subsampled": {"ndcg_at_1": 0.802, "ndcg_at_3": 0.85338, "ndcg_at_5": 0.86732, "ndcg_at_10": 0.87428, "ndcg_at_20": 0.88107, "ndcg_at_100": 0.88546, "ndcg_at_1000": 0.88657, "map_at_1": 0.802, "map_at_3": 0.84133, "map_at_5": 0.84903, "map_at_10": 0.85181, "map_at_20": 0.85379, "map_at_100": 0.8545, "map_at_1000": 0.85456, "recall_at_1": 0.802, "recall_at_3": 0.888, "recall_at_5": 0.922, "recall_at_10": 0.944, "recall_at_20": 0.97, "recall_at_100": 0.992, "recall_at_1000": 1.0, "precision_at_1": 0.802, "precision_at_3": 0.296, "precision_at_5": 0.1844, "precision_at_10": 0.0944, "precision_at_20": 0.0485, "precision_at_100": 0.00992, "precision_at_1000": 0.001, "mrr_at_1": 0.798, "mrr_at_3": 0.8393333333333333, "mrr_at_5": 0.8470333333333331, "mrr_at_10": 0.8496023809523807, "mrr_at_20": 0.8517748418248414, "mrr_at_100": 0.8525011699855726, "mrr_at_1000": 0.8525560625613932, "naucs_at_1_max": 0.7609787332735034, "naucs_at_1_std": -0.04982403775373434, "naucs_at_1_diff1": 0.9467323457935447, "naucs_at_3_max": 0.810834347943723, "naucs_at_3_std": -0.07579985119047568, "naucs_at_3_diff1": 0.9171401515151517, "naucs_at_5_max": 0.7709665062606241, "naucs_at_5_std": -0.1451076156958529, "naucs_at_5_diff1": 0.9040556393497581, "naucs_at_10_max": 0.8141923436041086, "naucs_at_10_std": 0.03956582633053216, "naucs_at_10_diff1": 0.9042950513538771, "naucs_at_20_max": 0.7773109243697499, "naucs_at_20_std": 0.03131030189853261, "naucs_at_20_diff1": 0.8921568627450983, "naucs_at_100_max": 0.9346405228758211, "naucs_at_100_std": 0.21288515406164388, "naucs_at_100_diff1": 0.8978758169934562, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.82143, "ndcg_at_3": 0.88078, "ndcg_at_5": 0.88662, "ndcg_at_10": 0.8959, "ndcg_at_20": 0.90245, "ndcg_at_100": 0.90455, "ndcg_at_1000": 0.90455, "map_at_1": 0.82143, "map_at_3": 0.86667, "map_at_5": 0.86988, "map_at_10": 0.87373, "map_at_20": 0.87564, "map_at_100": 0.87596, "map_at_1000": 0.87596, "recall_at_1": 0.82143, "recall_at_3": 0.92143, "recall_at_5": 0.93571, "recall_at_10": 0.96429, "recall_at_20": 0.98929, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.82143, "precision_at_3": 0.30714, "precision_at_5": 0.18714, "precision_at_10": 0.09643, "precision_at_20": 0.04946, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.825, "mrr_at_3": 0.867857142857143, "mrr_at_5": 0.8712500000000002, "mrr_at_10": 0.8749943310657597, "mrr_at_20": 0.8769510053438626, "mrr_at_100": 0.877276262150675, "mrr_at_1000": 0.877276262150675, "naucs_at_1_max": 0.42563899346146206, "naucs_at_1_std": 0.1471765405191198, "naucs_at_1_diff1": 0.8586387953239548, "naucs_at_3_max": 0.5611365758424587, "naucs_at_3_std": 0.3328664799253024, "naucs_at_3_diff1": 0.8272642390289456, "naucs_at_5_max": 0.514705882352943, "naucs_at_5_std": 0.30713766988277114, "naucs_at_5_diff1": 0.7961406784936206, "naucs_at_10_max": 0.6987394957983158, "naucs_at_10_std": 0.5981325863678804, "naucs_at_10_diff1": 0.7941176470588184, "naucs_at_20_max": 0.5659819483349039, "naucs_at_20_std": 0.38624338624340593, "naucs_at_20_diff1": 0.7222222222222332, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.63981, "ndcg_at_3": 0.74917, "ndcg_at_5": 0.7759, "ndcg_at_10": 0.79135, "ndcg_at_20": 0.79694, "ndcg_at_100": 0.8024, "ndcg_at_1000": 0.80405, "map_at_1": 0.63981, "map_at_3": 0.72269, "map_at_5": 0.73766, "map_at_10": 0.74409, "map_at_20": 0.74569, "map_at_100": 0.74649, "map_at_1000": 0.74657, "recall_at_1": 0.63981, "recall_at_3": 0.82562, "recall_at_5": 0.88996, "recall_at_10": 0.93746, "recall_at_20": 0.95911, "recall_at_100": 0.98797, "recall_at_1000": 1.0, "precision_at_1": 0.63981, "precision_at_3": 0.27521, "precision_at_5": 0.17799, "precision_at_10": 0.09375, "precision_at_20": 0.04796, "precision_at_100": 0.00988, "precision_at_1000": 0.001, "mrr_at_1": 0.6361996392062538, "mrr_at_3": 0.7217879334535983, "mrr_at_5": 0.7364902786129491, "mrr_at_10": 0.7432783075146278, "mrr_at_20": 0.7447440403539413, "mrr_at_100": 0.7455222233062115, "mrr_at_1000": 0.7456073710266525, "naucs_at_1_max": 0.1755436734128544, "naucs_at_1_std": -0.3413375494454732, "naucs_at_1_diff1": 0.8028659791349476, "naucs_at_3_max": 0.22498779700389868, "naucs_at_3_std": -0.3217234939830549, "naucs_at_3_diff1": 0.709972936200294, "naucs_at_5_max": 0.30088635417517934, "naucs_at_5_std": -0.18095101115377482, "naucs_at_5_diff1": 0.6729946219402011, "naucs_at_10_max": 0.45528821068686837, "naucs_at_10_std": 0.111949278381562, "naucs_at_10_diff1": 0.5970873099232054, "naucs_at_20_max": 0.5130688154968079, "naucs_at_20_std": 0.1996874580648595, "naucs_at_20_diff1": 0.5824718780309613, "naucs_at_100_max": 0.6356023548124133, "naucs_at_100_std": 0.6258417323163146, "naucs_at_100_diff1": 0.5270310843892404, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.72, "ndcg_at_3": 0.85988, "ndcg_at_5": 0.85988, "ndcg_at_10": 0.86948, "ndcg_at_20": 0.87204, "ndcg_at_100": 0.87396, "ndcg_at_1000": 0.87396, "map_at_1": 0.72, "map_at_3": 0.82833, "map_at_5": 0.82833, "map_at_10": 0.83225, "map_at_20": 0.83296, "map_at_100": 0.83324, "map_at_1000": 0.83324, "recall_at_1": 0.72, "recall_at_3": 0.95, "recall_at_5": 0.95, "recall_at_10": 0.98, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.72, "precision_at_3": 0.31667, "precision_at_5": 0.19, "precision_at_10": 0.098, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.75, "mrr_at_3": 0.845, "mrr_at_5": 0.845, "mrr_at_10": 0.849095238095238, "mrr_at_20": 0.8498095238095238, "mrr_at_100": 0.850095238095238, "mrr_at_1000": 0.850095238095238, "naucs_at_1_max": -0.0836195054945053, "naucs_at_1_std": -0.565399877899878, "naucs_at_1_diff1": 0.7036210317460321, "naucs_at_3_max": 0.17889822595705038, "naucs_at_3_std": -0.12530345471521812, "naucs_at_3_diff1": 0.6112044817927178, "naucs_at_5_max": 0.1788982259570549, "naucs_at_5_std": -0.12530345471521045, "naucs_at_5_diff1": 0.6112044817927212, "naucs_at_10_max": -0.5929038281979383, "naucs_at_10_std": -0.5929038281979383, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": -1.7399626517273863, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"151646": {
|
29 |
+
"content": "<|object_ref_start|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"151647": {
|
37 |
+
"content": "<|object_ref_end|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"151648": {
|
45 |
+
"content": "<|box_start|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"151649": {
|
53 |
+
"content": "<|box_end|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"151650": {
|
61 |
+
"content": "<|quad_start|>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"151651": {
|
69 |
+
"content": "<|quad_end|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"151652": {
|
77 |
+
"content": "<|vision_start|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"151653": {
|
85 |
+
"content": "<|vision_end|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"151654": {
|
93 |
+
"content": "<|vision_pad|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"151655": {
|
101 |
+
"content": "<|image_pad|>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"151656": {
|
109 |
+
"content": "<|video_pad|>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
}
|
116 |
+
},
|
117 |
+
"additional_special_tokens": [
|
118 |
+
"<|im_start|>",
|
119 |
+
"<|im_end|>",
|
120 |
+
"<|object_ref_start|>",
|
121 |
+
"<|object_ref_end|>",
|
122 |
+
"<|box_start|>",
|
123 |
+
"<|box_end|>",
|
124 |
+
"<|quad_start|>",
|
125 |
+
"<|quad_end|>",
|
126 |
+
"<|vision_start|>",
|
127 |
+
"<|vision_end|>",
|
128 |
+
"<|vision_pad|>",
|
129 |
+
"<|image_pad|>",
|
130 |
+
"<|video_pad|>"
|
131 |
+
],
|
132 |
+
"bos_token": null,
|
133 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
134 |
+
"clean_up_tokenization_spaces": false,
|
135 |
+
"eos_token": "<|im_end|>",
|
136 |
+
"errors": "replace",
|
137 |
+
"model_max_length": 32768,
|
138 |
+
"pad_token": "<|endoftext|>",
|
139 |
+
"padding_side": "left",
|
140 |
+
"processor_class": "ColQwen2Processor",
|
141 |
+
"split_special_tokens": false,
|
142 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
143 |
+
"unk_token": null
|
144 |
+
}
|
training_config.yml
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
config:
|
2 |
+
(): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
|
3 |
+
output_dir: !path ../../../models/colqwen2-5e
|
4 |
+
processor:
|
5 |
+
(): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
|
6 |
+
class_to_instanciate: !ext colpali_engine.models.ColQwen2Processor
|
7 |
+
pretrained_model_name_or_path: "./models/colqwen2_base" # "./models/paligemma-3b-mix-448"
|
8 |
+
# max_length: 50
|
9 |
+
|
10 |
+
model:
|
11 |
+
(): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
|
12 |
+
class_to_instanciate: !ext colpali_engine.models.ColQwen2
|
13 |
+
pretrained_model_name_or_path: "./models/colqwen2_base"
|
14 |
+
torch_dtype: !ext torch.bfloat16
|
15 |
+
use_cache: false
|
16 |
+
# device_map: "auto"
|
17 |
+
# quantization_config:
|
18 |
+
# (): transformers.BitsAndBytesConfig
|
19 |
+
# load_in_4bit: true
|
20 |
+
# bnb_4bit_quant_type: "nf4"
|
21 |
+
# bnb_4bit_compute_dtype: "bfloat16"
|
22 |
+
# bnb_4bit_use_double_quant: true
|
23 |
+
|
24 |
+
dataset_loading_func: !ext colpali_engine.utils.dataset_transformation.load_train_set_detailed
|
25 |
+
eval_dataset_loader: !import ../data/test_data.yaml
|
26 |
+
|
27 |
+
# max_length: 50
|
28 |
+
run_eval: true
|
29 |
+
add_suffix: true
|
30 |
+
loss_func:
|
31 |
+
(): colpali_engine.loss.late_interaction_losses.ColbertPairwiseCELoss
|
32 |
+
tr_args:
|
33 |
+
(): transformers.training_args.TrainingArguments
|
34 |
+
output_dir: null
|
35 |
+
overwrite_output_dir: true
|
36 |
+
num_train_epochs: 5
|
37 |
+
per_device_train_batch_size: 4
|
38 |
+
# 6 x 8 gpus = 48 batch size
|
39 |
+
# gradient_accumulation_steps: 4
|
40 |
+
per_device_eval_batch_size: 4
|
41 |
+
eval_strategy: "steps"
|
42 |
+
# dataloader_num_workers: 8
|
43 |
+
# bf16: true
|
44 |
+
save_steps: 500
|
45 |
+
logging_steps: 10
|
46 |
+
eval_steps: 100
|
47 |
+
warmup_steps: 500
|
48 |
+
learning_rate: 5e-5
|
49 |
+
save_total_limit: 1
|
50 |
+
resume_from_checkpoint: true
|
51 |
+
# optim: "paged_adamw_8bit"
|
52 |
+
|
53 |
+
peft_config:
|
54 |
+
(): peft.LoraConfig
|
55 |
+
r: 32
|
56 |
+
lora_alpha: 32
|
57 |
+
lora_dropout: 0.1
|
58 |
+
init_lora_weights: "gaussian"
|
59 |
+
bias: "none"
|
60 |
+
task_type: "FEATURE_EXTRACTION"
|
61 |
+
target_modules: '(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
|
62 |
+
# target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
|
63 |
+
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|