Push model using huggingface_hub.
Browse files- 1_Pooling/config.json +10 -0
- README.md +396 -0
- config.json +61 -0
- config_sentence_transformers.json +14 -0
- config_setfit.json +68 -0
- configuration_hf_nomic_bert.py +56 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modeling_hf_nomic_bert.py +0 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 768,
|
| 3 |
+
"pooling_mode_cls_token": false,
|
| 4 |
+
"pooling_mode_mean_tokens": true,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,396 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- setfit
|
| 4 |
+
- sentence-transformers
|
| 5 |
+
- text-classification
|
| 6 |
+
- generated_from_setfit_trainer
|
| 7 |
+
widget:
|
| 8 |
+
- text: Insert a descriptive caption for the image
|
| 9 |
+
- text: Make the photo lighter
|
| 10 |
+
- text: Move the logo to the top layer
|
| 11 |
+
- text: Make the shape smaller
|
| 12 |
+
- text: Flip the icon vertically
|
| 13 |
+
metrics:
|
| 14 |
+
- accuracy
|
| 15 |
+
pipeline_tag: text-classification
|
| 16 |
+
library_name: setfit
|
| 17 |
+
inference: true
|
| 18 |
+
base_model: nomic-ai/nomic-embed-text-v1.5
|
| 19 |
+
model-index:
|
| 20 |
+
- name: SetFit with nomic-ai/nomic-embed-text-v1.5
|
| 21 |
+
results:
|
| 22 |
+
- task:
|
| 23 |
+
type: text-classification
|
| 24 |
+
name: Text Classification
|
| 25 |
+
dataset:
|
| 26 |
+
name: Unknown
|
| 27 |
+
type: unknown
|
| 28 |
+
split: test
|
| 29 |
+
metrics:
|
| 30 |
+
- type: accuracy
|
| 31 |
+
value: 0.5701459034792368
|
| 32 |
+
name: Accuracy
|
| 33 |
+
---
|
| 34 |
+
|
| 35 |
+
# SetFit with nomic-ai/nomic-embed-text-v1.5
|
| 36 |
+
|
| 37 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
| 38 |
+
|
| 39 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
| 40 |
+
|
| 41 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
| 42 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
| 43 |
+
|
| 44 |
+
## Model Details
|
| 45 |
+
|
| 46 |
+
### Model Description
|
| 47 |
+
- **Model Type:** SetFit
|
| 48 |
+
- **Sentence Transformer body:** [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5)
|
| 49 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
| 50 |
+
- **Maximum Sequence Length:** 8192 tokens
|
| 51 |
+
- **Number of Classes:** 63 classes
|
| 52 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 53 |
+
<!-- - **Language:** Unknown -->
|
| 54 |
+
<!-- - **License:** Unknown -->
|
| 55 |
+
|
| 56 |
+
### Model Sources
|
| 57 |
+
|
| 58 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
| 59 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
| 60 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 61 |
+
|
| 62 |
+
### Model Labels
|
| 63 |
+
| Label | Examples |
|
| 64 |
+
|:---------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 65 |
+
| setBorderStyle | <ul><li>'Change the border color to red'</li><li>'Change the border to a pattern'</li><li>'Add a shadow border'</li></ul> |
|
| 66 |
+
| setChildIndex | <ul><li>'Bring the shape to the front'</li><li>'Send the watermark to the back'</li><li>'Bring the button to the front'</li></ul> |
|
| 67 |
+
| undo | <ul><li>'Go back to the original position'</li><li>'Revert the color change'</li><li>'Go back to the original text'</li></ul> |
|
| 68 |
+
| setTextListStyle | <ul><li>'Make the text into bullet points'</li><li>'Convert the text to a list format'</li><li>'Create a bulleted list from the text'</li></ul> |
|
| 69 |
+
| align | <ul><li>'Align all the text elements to the left'</li><li>'Align the images to the right edge'</li><li>'Center align the images on the page'</li></ul> |
|
| 70 |
+
| resetImageSettings | <ul><li>'Remove all edits from the photo'</li><li>'Reset the image to original'</li><li>'Restore the original colors'</li></ul> |
|
| 71 |
+
| rotate | <ul><li>'Turn the logo upside down'</li><li>'Rotate the text 45 degrees'</li><li>'Turn the button around'</li></ul> |
|
| 72 |
+
| ungroup | <ul><li>'Ungroup the combined items'</li><li>'Separate the grouped items'</li><li>'Break apart the grouped components'</li></ul> |
|
| 73 |
+
| setBlendMode | <ul><li>'Set the blend mode to multiply'</li><li>'Change the blend mode to lighten'</li><li>'Set the blend mode to color dodge'</li></ul> |
|
| 74 |
+
| addText | <ul><li>'Add a navigation menu text'</li><li>'Insert a descriptive caption for the image'</li><li>'Add a date and time for the event'</li></ul> |
|
| 75 |
+
| setParagraphSpacing | <ul><li>'Add more paragraph separation'</li><li>'Increase the paragraph gap'</li><li>'Make the text sections tighter'</li></ul> |
|
| 76 |
+
| addAsset | <ul><li>'Add a sports-themed background'</li><li>'Add a tech-themed icon pack'</li><li>'Add a colorful gradient background'</li></ul> |
|
| 77 |
+
| addAssetsUIAction | <ul><li>'I need some decorative elements'</li><li>'I need some professional-looking assets'</li><li>'Can you recommend some images that would work well here?'</li></ul> |
|
| 78 |
+
| redo | <ul><li>'Bring back the original text'</li><li>'Redo the text edit'</li><li>'Redo the last modification'</li></ul> |
|
| 79 |
+
| applyAnimationObjectPreset | <ul><li>'Make the image slide from left'</li><li>'Add a fade-in animation to the text'</li><li>'Add a slide-up animation'</li></ul> |
|
| 80 |
+
| moveRelativeTo | <ul><li>'Move the button to the right'</li><li>'Position the image above the text'</li><li>'Move the shape to the bottom'</li></ul> |
|
| 81 |
+
| resizePage | <ul><li>'Make the page taller'</li><li>'Resize to LinkedIn post dimensions'</li><li>'Make the page portrait orientation'</li></ul> |
|
| 82 |
+
| setBlur | <ul><li>'Blur the logo slightly'</li><li>'Blur the background elements'</li><li>'Add a gaussian blur'</li></ul> |
|
| 83 |
+
| group | <ul><li>'Group the header elements'</li><li>'Group the footer content'</li><li>'Combine the logo and tagline'</li></ul> |
|
| 84 |
+
| displayHelpQA | <ul><li>'How do I group elements together?'</li><li>'How do I add shadows to text?'</li><li>'How can I duplicate elements?'</li></ul> |
|
| 85 |
+
| applyPageLevelAnimation | <ul><li>'Make the page slide in from the right'</li><li>'Add a flip animation to the whole page'</li><li>'Make the page scale in smoothly'</li></ul> |
|
| 86 |
+
| duplicatePage | <ul><li>'Duplicate the page structure'</li><li>'Duplicate the current layout'</li><li>'Make a second version'</li></ul> |
|
| 87 |
+
| setBackgroundColor | <ul><li>'Set the background to cool blue'</li><li>'Change to a dark background'</li><li>'Change to a neutral background'</li></ul> |
|
| 88 |
+
| setLetterSpacing | <ul><li>'Increase spacing between characters'</li><li>'Tighten the letter spacing'</li><li>'Make the text more spaced out'</li></ul> |
|
| 89 |
+
| setWarmth | <ul><li>'Add warm lighting to the image'</li><li>'Make the photo more golden'</li><li>'Make the image more yellow'</li></ul> |
|
| 90 |
+
| setSaturation | <ul><li>'Make the image more muted'</li><li>'Increase the color richness'</li><li>'Reduce the color vibrancy'</li></ul> |
|
| 91 |
+
| replaceText | <ul><li>'Replace the title'</li><li>'Update the navigation text'</li><li>'Replace the menu items'</li></ul> |
|
| 92 |
+
| setLineSpacing | <ul><li>'Increase spacing between lines'</li><li>'Make the text more compact'</li><li>'Make the lines tighter'</li></ul> |
|
| 93 |
+
| setSharpness | <ul><li>'Sharpen the image details'</li><li>'Sharpen the image edges'</li><li>'Increase the detail sharpness'</li></ul> |
|
| 94 |
+
| delete | <ul><li>'Remove the background shape'</li><li>'Delete the broken image'</li><li>'Remove the unnecessary decoration'</li></ul> |
|
| 95 |
+
| setContrast | <ul><li>'Make the colors more vibrant'</li><li>'Make the image more intense'</li><li>'Make the image more striking'</li></ul> |
|
| 96 |
+
| setTextLayout | <ul><li>'Create text that follows a circle'</li><li>'Create circular text around the logo'</li><li>'Make the text follow a custom curve'</li></ul> |
|
| 97 |
+
| generateImageFromText | <ul><li>'Make an image of a vintage car'</li><li>'Generate a picture of a tropical beach'</li><li>'Make an image of a magical forest'</li></ul> |
|
| 98 |
+
| flip | <ul><li>'Flip the text vertically'</li><li>'Flip the icon vertically'</li><li>'Mirror the logo vertically'</li></ul> |
|
| 99 |
+
| generateTemplates | <ul><li>'Create a wedding invitation with floral decorations'</li><li>'Generate a poster for a birthday party'</li><li>'Create a minimalistic menu for a restaurant'</li></ul> |
|
| 100 |
+
| setHighlight | <ul><li>'Enhance the highlight details'</li><li>'Make the highlights more prominent'</li><li>'Brighten the reflective areas'</li></ul> |
|
| 101 |
+
| removeBackground | <ul><li>'Remove the background from the illustration'</li><li>'Remove the background from the item'</li><li>'Remove the background from the animal'</li></ul> |
|
| 102 |
+
| fixTypography | <ul><li>'Fix the letter spacing'</li><li>'Improve the overall typography'</li><li>'Fix the typographic errors'</li></ul> |
|
| 103 |
+
| setBrightness | <ul><li>'Brighten the highlights'</li><li>'Make the image more luminous'</li><li>'Increase the brightness contrast'</li></ul> |
|
| 104 |
+
| changeContentInImage | <ul><li>"Add glasses to the person's face"</li><li>'Remove the logo from the shirt'</li><li>'Add a scarf to the person'</li></ul> |
|
| 105 |
+
| setImageAsBackground | <ul><li>'Make the photo cover the background'</li><li>'Set the photo as page background'</li><li>'Set the picture as full background'</li></ul> |
|
| 106 |
+
| resize | <ul><li>'Reduce the shape size'</li><li>'Make the image larger'</li><li>'Make the shape smaller'</li></ul> |
|
| 107 |
+
| setFontSize | <ul><li>'Make the heading larger'</li><li>'Make the label smaller'</li><li>'Make the quote larger'</li></ul> |
|
| 108 |
+
| showUploadUI | <ul><li>'Show me the upload options'</li><li>'I need to import a file'</li><li>'I want to import an image'</li></ul> |
|
| 109 |
+
| replaceAsset | <ul><li>'Change the decorative element'</li><li>'Change the shape to a different style'</li><li>'Replace the element with an alternative'</li></ul> |
|
| 110 |
+
| distributeAroundObject | <ul><li>'Distribute the text around the focal point'</li><li>'Distribute the elements around the focal point'</li><li>'Place the decorations around the title'</li></ul> |
|
| 111 |
+
| select | <ul><li>'Pick the main text block'</li><li>'Select the logo element'</li><li>'Select the footer content'</li></ul> |
|
| 112 |
+
| setOpacity | <ul><li>'Make the shape more opaque'</li><li>'Reduce the opacity of the shape'</li><li>'Make the background more opaque'</li></ul> |
|
| 113 |
+
| setDropShadow | <ul><li>'Add a long shadow effect'</li><li>'Add a gradient shadow'</li><li>'Create a realistic shadow'</li></ul> |
|
| 114 |
+
| proposeAssets | <ul><li>'Suggest some shape designs'</li><li>'Show me pattern options'</li><li>'Find me some background images'</li></ul> |
|
| 115 |
+
| setShadow | <ul><li>'Increase the shadow intensity'</li><li>'Make the shadows deeper'</li><li>'Make the shadows more prominent'</li></ul> |
|
| 116 |
+
| setCropShape | <ul><li>'Crop the image to a circle'</li><li>'Make the image rectangular'</li><li>'Crop to a custom shape'</li></ul> |
|
| 117 |
+
| setTextAlignment | <ul><li>'Justify the description'</li><li>'Center the tagline'</li><li>'Left align the subtitle'</li></ul> |
|
| 118 |
+
| setFontStyle | <ul><li>'Make the text italic and bold'</li><li>'Make the text bold and underlined'</li><li>'Add bold to the title'</li></ul> |
|
| 119 |
+
| duplicateSceneNode | <ul><li>'Copy the button and resize it'</li><li>'Duplicate the text and change the color'</li><li>'Copy the text and modify it'</li></ul> |
|
| 120 |
+
| setFontType | <ul><li>'Change the font to Arial'</li><li>'Use a script font for the title'</li><li>'Use a minimalist font'</li></ul> |
|
| 121 |
+
| setTextDecorationEffect | <ul><li>'Create a text container'</li><li>'Add a glow effect behind the text'</li><li>'Add a highlight background to the text'</li></ul> |
|
| 122 |
+
| scatter | <ul><li>'Randomly place the icons on the page'</li><li>'Distribute the bubbles randomly'</li><li>'Scatter the stars around the title'</li></ul> |
|
| 123 |
+
| removeContentFromImage | <ul><li>'Delete the unwanted person'</li><li>'Delete the car from the image'</li><li>'Remove the distracting element'</li></ul> |
|
| 124 |
+
| setFillColor | <ul><li>'Fill the element with lime'</li><li>'Change the text color to pink'</li><li>'Change the color to teal'</li></ul> |
|
| 125 |
+
| setTextShadow | <ul><li>'Create a text shadow'</li><li>'Add a dramatic shadow effect'</li><li>'Add a glow effect to the text'</li></ul> |
|
| 126 |
+
| previewFilterEffects | <ul><li>'Add a dramatic contrast effect'</li><li>'Make the image pop with color'</li><li>'Apply a cool blue filter'</li></ul> |
|
| 127 |
+
| duplicateSceneNodeToPage | <ul><li>'Copy the content to the final page'</li><li>'Duplicate the decoration to page 8'</li><li>'Copy the icon to the next slide'</li></ul> |
|
| 128 |
+
|
| 129 |
+
## Evaluation
|
| 130 |
+
|
| 131 |
+
### Metrics
|
| 132 |
+
| Label | Accuracy |
|
| 133 |
+
|:--------|:---------|
|
| 134 |
+
| **all** | 0.5701 |
|
| 135 |
+
|
| 136 |
+
## Uses
|
| 137 |
+
|
| 138 |
+
### Direct Use for Inference
|
| 139 |
+
|
| 140 |
+
First install the SetFit library:
|
| 141 |
+
|
| 142 |
+
```bash
|
| 143 |
+
pip install setfit
|
| 144 |
+
```
|
| 145 |
+
|
| 146 |
+
Then you can load this model and run inference.
|
| 147 |
+
|
| 148 |
+
```python
|
| 149 |
+
from setfit import SetFitModel
|
| 150 |
+
|
| 151 |
+
# Download from the 🤗 Hub
|
| 152 |
+
model = SetFitModel.from_pretrained("setfit_model_id")
|
| 153 |
+
# Run inference
|
| 154 |
+
preds = model("Make the photo lighter")
|
| 155 |
+
```
|
| 156 |
+
|
| 157 |
+
<!--
|
| 158 |
+
### Downstream Use
|
| 159 |
+
|
| 160 |
+
*List how someone could finetune this model on their own dataset.*
|
| 161 |
+
-->
|
| 162 |
+
|
| 163 |
+
<!--
|
| 164 |
+
### Out-of-Scope Use
|
| 165 |
+
|
| 166 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 167 |
+
-->
|
| 168 |
+
|
| 169 |
+
<!--
|
| 170 |
+
## Bias, Risks and Limitations
|
| 171 |
+
|
| 172 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 173 |
+
-->
|
| 174 |
+
|
| 175 |
+
<!--
|
| 176 |
+
### Recommendations
|
| 177 |
+
|
| 178 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 179 |
+
-->
|
| 180 |
+
|
| 181 |
+
## Training Details
|
| 182 |
+
|
| 183 |
+
### Training Set Metrics
|
| 184 |
+
| Training set | Min | Median | Max |
|
| 185 |
+
|:-------------|:----|:-------|:----|
|
| 186 |
+
| Word count | 3 | 5.2063 | 11 |
|
| 187 |
+
|
| 188 |
+
| Label | Training Sample Count |
|
| 189 |
+
|:---------------------------|:----------------------|
|
| 190 |
+
| addAsset | 8 |
|
| 191 |
+
| addAssetsUIAction | 8 |
|
| 192 |
+
| addText | 8 |
|
| 193 |
+
| align | 8 |
|
| 194 |
+
| applyAnimationObjectPreset | 8 |
|
| 195 |
+
| applyPageLevelAnimation | 8 |
|
| 196 |
+
| changeContentInImage | 8 |
|
| 197 |
+
| delete | 8 |
|
| 198 |
+
| displayHelpQA | 8 |
|
| 199 |
+
| distributeAroundObject | 8 |
|
| 200 |
+
| duplicatePage | 8 |
|
| 201 |
+
| duplicateSceneNode | 8 |
|
| 202 |
+
| duplicateSceneNodeToPage | 8 |
|
| 203 |
+
| fixTypography | 8 |
|
| 204 |
+
| flip | 8 |
|
| 205 |
+
| generateImageFromText | 8 |
|
| 206 |
+
| generateTemplates | 8 |
|
| 207 |
+
| group | 8 |
|
| 208 |
+
| moveRelativeTo | 8 |
|
| 209 |
+
| previewFilterEffects | 8 |
|
| 210 |
+
| proposeAssets | 8 |
|
| 211 |
+
| redo | 8 |
|
| 212 |
+
| removeBackground | 8 |
|
| 213 |
+
| removeContentFromImage | 8 |
|
| 214 |
+
| replaceAsset | 8 |
|
| 215 |
+
| replaceText | 8 |
|
| 216 |
+
| resetImageSettings | 8 |
|
| 217 |
+
| resize | 8 |
|
| 218 |
+
| resizePage | 8 |
|
| 219 |
+
| rotate | 8 |
|
| 220 |
+
| scatter | 8 |
|
| 221 |
+
| select | 8 |
|
| 222 |
+
| setBackgroundColor | 8 |
|
| 223 |
+
| setBlendMode | 8 |
|
| 224 |
+
| setBlur | 8 |
|
| 225 |
+
| setBorderStyle | 8 |
|
| 226 |
+
| setBrightness | 8 |
|
| 227 |
+
| setChildIndex | 8 |
|
| 228 |
+
| setContrast | 8 |
|
| 229 |
+
| setCropShape | 8 |
|
| 230 |
+
| setDropShadow | 8 |
|
| 231 |
+
| setFillColor | 8 |
|
| 232 |
+
| setFontSize | 8 |
|
| 233 |
+
| setFontStyle | 8 |
|
| 234 |
+
| setFontType | 8 |
|
| 235 |
+
| setHighlight | 8 |
|
| 236 |
+
| setImageAsBackground | 8 |
|
| 237 |
+
| setLetterSpacing | 8 |
|
| 238 |
+
| setLineSpacing | 8 |
|
| 239 |
+
| setOpacity | 8 |
|
| 240 |
+
| setParagraphSpacing | 8 |
|
| 241 |
+
| setSaturation | 8 |
|
| 242 |
+
| setShadow | 8 |
|
| 243 |
+
| setSharpness | 8 |
|
| 244 |
+
| setTextAlignment | 8 |
|
| 245 |
+
| setTextDecorationEffect | 8 |
|
| 246 |
+
| setTextLayout | 8 |
|
| 247 |
+
| setTextListStyle | 8 |
|
| 248 |
+
| setTextShadow | 8 |
|
| 249 |
+
| setWarmth | 8 |
|
| 250 |
+
| showUploadUI | 8 |
|
| 251 |
+
| undo | 8 |
|
| 252 |
+
| ungroup | 8 |
|
| 253 |
+
|
| 254 |
+
### Training Hyperparameters
|
| 255 |
+
- batch_size: (64, 64)
|
| 256 |
+
- num_epochs: (1, 1)
|
| 257 |
+
- max_steps: -1
|
| 258 |
+
- sampling_strategy: oversampling
|
| 259 |
+
- body_learning_rate: (2e-05, 1e-05)
|
| 260 |
+
- head_learning_rate: 0.01
|
| 261 |
+
- loss: CosineSimilarityLoss
|
| 262 |
+
- distance_metric: cosine_distance
|
| 263 |
+
- margin: 0.25
|
| 264 |
+
- end_to_end: False
|
| 265 |
+
- use_amp: False
|
| 266 |
+
- warmup_proportion: 0.1
|
| 267 |
+
- l2_weight: 0.01
|
| 268 |
+
- seed: 42
|
| 269 |
+
- eval_max_steps: -1
|
| 270 |
+
- load_best_model_at_end: False
|
| 271 |
+
|
| 272 |
+
### Training Results
|
| 273 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
| 274 |
+
|:------:|:----:|:-------------:|:---------------:|
|
| 275 |
+
| 0.0003 | 1 | 0.1733 | - |
|
| 276 |
+
| 0.0128 | 50 | 0.1425 | - |
|
| 277 |
+
| 0.0256 | 100 | 0.0954 | - |
|
| 278 |
+
| 0.0384 | 150 | 0.0483 | - |
|
| 279 |
+
| 0.0512 | 200 | 0.0297 | - |
|
| 280 |
+
| 0.0640 | 250 | 0.0189 | - |
|
| 281 |
+
| 0.0768 | 300 | 0.0122 | - |
|
| 282 |
+
| 0.0896 | 350 | 0.0099 | - |
|
| 283 |
+
| 0.1024 | 400 | 0.0085 | - |
|
| 284 |
+
| 0.1152 | 450 | 0.0067 | - |
|
| 285 |
+
| 0.1280 | 500 | 0.0059 | - |
|
| 286 |
+
| 0.1408 | 550 | 0.0076 | - |
|
| 287 |
+
| 0.1536 | 600 | 0.0061 | - |
|
| 288 |
+
| 0.1664 | 650 | 0.0049 | - |
|
| 289 |
+
| 0.1792 | 700 | 0.003 | - |
|
| 290 |
+
| 0.1920 | 750 | 0.0023 | - |
|
| 291 |
+
| 0.2048 | 800 | 0.002 | - |
|
| 292 |
+
| 0.2176 | 850 | 0.0037 | - |
|
| 293 |
+
| 0.2304 | 900 | 0.0007 | - |
|
| 294 |
+
| 0.2432 | 950 | 0.0015 | - |
|
| 295 |
+
| 0.2560 | 1000 | 0.0017 | - |
|
| 296 |
+
| 0.2688 | 1050 | 0.0014 | - |
|
| 297 |
+
| 0.2816 | 1100 | 0.0003 | - |
|
| 298 |
+
| 0.2944 | 1150 | 0.0006 | - |
|
| 299 |
+
| 0.3072 | 1200 | 0.001 | - |
|
| 300 |
+
| 0.3200 | 1250 | 0.0007 | - |
|
| 301 |
+
| 0.3328 | 1300 | 0.0002 | - |
|
| 302 |
+
| 0.3456 | 1350 | 0.0012 | - |
|
| 303 |
+
| 0.3584 | 1400 | 0.0006 | - |
|
| 304 |
+
| 0.3712 | 1450 | 0.0003 | - |
|
| 305 |
+
| 0.3840 | 1500 | 0.0005 | - |
|
| 306 |
+
| 0.3968 | 1550 | 0.0002 | - |
|
| 307 |
+
| 0.4096 | 1600 | 0.0004 | - |
|
| 308 |
+
| 0.4224 | 1650 | 0.0009 | - |
|
| 309 |
+
| 0.4352 | 1700 | 0.0007 | - |
|
| 310 |
+
| 0.4480 | 1750 | 0.0003 | - |
|
| 311 |
+
| 0.4608 | 1800 | 0.0001 | - |
|
| 312 |
+
| 0.4736 | 1850 | 0.0006 | - |
|
| 313 |
+
| 0.4864 | 1900 | 0.0004 | - |
|
| 314 |
+
| 0.4992 | 1950 | 0.0004 | - |
|
| 315 |
+
| 0.5120 | 2000 | 0.0001 | - |
|
| 316 |
+
| 0.5248 | 2050 | 0.0004 | - |
|
| 317 |
+
| 0.5376 | 2100 | 0.0003 | - |
|
| 318 |
+
| 0.5504 | 2150 | 0.0012 | - |
|
| 319 |
+
| 0.5632 | 2200 | 0.0006 | - |
|
| 320 |
+
| 0.5760 | 2250 | 0.0001 | - |
|
| 321 |
+
| 0.5888 | 2300 | 0.0003 | - |
|
| 322 |
+
| 0.6016 | 2350 | 0.0007 | - |
|
| 323 |
+
| 0.6144 | 2400 | 0.0003 | - |
|
| 324 |
+
| 0.6272 | 2450 | 0.0004 | - |
|
| 325 |
+
| 0.6400 | 2500 | 0.0006 | - |
|
| 326 |
+
| 0.6528 | 2550 | 0.0001 | - |
|
| 327 |
+
| 0.6656 | 2600 | 0.0003 | - |
|
| 328 |
+
| 0.6784 | 2650 | 0.0006 | - |
|
| 329 |
+
| 0.6912 | 2700 | 0.001 | - |
|
| 330 |
+
| 0.7040 | 2750 | 0.0004 | - |
|
| 331 |
+
| 0.7168 | 2800 | 0.0008 | - |
|
| 332 |
+
| 0.7296 | 2850 | 0.0003 | - |
|
| 333 |
+
| 0.7424 | 2900 | 0.0007 | - |
|
| 334 |
+
| 0.7552 | 2950 | 0.0007 | - |
|
| 335 |
+
| 0.7680 | 3000 | 0.0007 | - |
|
| 336 |
+
| 0.7808 | 3050 | 0.0003 | - |
|
| 337 |
+
| 0.7937 | 3100 | 0.0003 | - |
|
| 338 |
+
| 0.8065 | 3150 | 0.0003 | - |
|
| 339 |
+
| 0.8193 | 3200 | 0.0007 | - |
|
| 340 |
+
| 0.8321 | 3250 | 0.0001 | - |
|
| 341 |
+
| 0.8449 | 3300 | 0.0006 | - |
|
| 342 |
+
| 0.8577 | 3350 | 0.0007 | - |
|
| 343 |
+
| 0.8705 | 3400 | 0.0003 | - |
|
| 344 |
+
| 0.8833 | 3450 | 0.0009 | - |
|
| 345 |
+
| 0.8961 | 3500 | 0.0003 | - |
|
| 346 |
+
| 0.9089 | 3550 | 0.0004 | - |
|
| 347 |
+
| 0.9217 | 3600 | 0.0004 | - |
|
| 348 |
+
| 0.9345 | 3650 | 0.0001 | - |
|
| 349 |
+
| 0.9473 | 3700 | 0.0001 | - |
|
| 350 |
+
| 0.9601 | 3750 | 0.0007 | - |
|
| 351 |
+
| 0.9729 | 3800 | 0.0006 | - |
|
| 352 |
+
| 0.9857 | 3850 | 0.0005 | - |
|
| 353 |
+
| 0.9985 | 3900 | 0.0003 | - |
|
| 354 |
+
|
| 355 |
+
### Framework Versions
|
| 356 |
+
- Python: 3.12.11
|
| 357 |
+
- SetFit: 1.1.3
|
| 358 |
+
- Sentence Transformers: 5.1.0
|
| 359 |
+
- Transformers: 4.54.1
|
| 360 |
+
- PyTorch: 2.7.1
|
| 361 |
+
- Datasets: 4.0.0
|
| 362 |
+
- Tokenizers: 0.21.4
|
| 363 |
+
|
| 364 |
+
## Citation
|
| 365 |
+
|
| 366 |
+
### BibTeX
|
| 367 |
+
```bibtex
|
| 368 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
| 369 |
+
doi = {10.48550/ARXIV.2209.11055},
|
| 370 |
+
url = {https://arxiv.org/abs/2209.11055},
|
| 371 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
| 372 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
| 373 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
| 374 |
+
publisher = {arXiv},
|
| 375 |
+
year = {2022},
|
| 376 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
| 377 |
+
}
|
| 378 |
+
```
|
| 379 |
+
|
| 380 |
+
<!--
|
| 381 |
+
## Glossary
|
| 382 |
+
|
| 383 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 384 |
+
-->
|
| 385 |
+
|
| 386 |
+
<!--
|
| 387 |
+
## Model Card Authors
|
| 388 |
+
|
| 389 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 390 |
+
-->
|
| 391 |
+
|
| 392 |
+
<!--
|
| 393 |
+
## Model Card Contact
|
| 394 |
+
|
| 395 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 396 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "swiglu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"NomicBertModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_hf_nomic_bert.NomicBertConfig",
|
| 9 |
+
"AutoModel": "modeling_hf_nomic_bert.NomicBertModel",
|
| 10 |
+
"AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining",
|
| 11 |
+
"AutoModelForMultipleChoice": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForMultipleChoice",
|
| 12 |
+
"AutoModelForQuestionAnswering": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForQuestionAnswering",
|
| 13 |
+
"AutoModelForSequenceClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForSequenceClassification",
|
| 14 |
+
"AutoModelForTokenClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForTokenClassification"
|
| 15 |
+
},
|
| 16 |
+
"bos_token_id": null,
|
| 17 |
+
"causal": false,
|
| 18 |
+
"dense_seq_output": true,
|
| 19 |
+
"embd_pdrop": 0.0,
|
| 20 |
+
"eos_token_id": null,
|
| 21 |
+
"fused_bias_fc": true,
|
| 22 |
+
"fused_dropout_add_ln": true,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"layer_norm_epsilon": 1e-12,
|
| 25 |
+
"max_trained_positions": 2048,
|
| 26 |
+
"mlp_fc1_bias": false,
|
| 27 |
+
"mlp_fc2_bias": false,
|
| 28 |
+
"model_type": "nomic_bert",
|
| 29 |
+
"n_embd": 768,
|
| 30 |
+
"n_head": 12,
|
| 31 |
+
"n_inner": 3072,
|
| 32 |
+
"n_layer": 12,
|
| 33 |
+
"n_positions": 8192,
|
| 34 |
+
"pad_vocab_size_multiple": 64,
|
| 35 |
+
"parallel_block": false,
|
| 36 |
+
"parallel_block_tied_norm": false,
|
| 37 |
+
"prenorm": false,
|
| 38 |
+
"qkv_proj_bias": false,
|
| 39 |
+
"reorder_and_upcast_attn": false,
|
| 40 |
+
"resid_pdrop": 0.0,
|
| 41 |
+
"rotary_emb_base": 1000,
|
| 42 |
+
"rotary_emb_fraction": 1.0,
|
| 43 |
+
"rotary_emb_interleaved": false,
|
| 44 |
+
"rotary_emb_scale_base": null,
|
| 45 |
+
"rotary_scaling_factor": null,
|
| 46 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 47 |
+
"scale_attn_weights": true,
|
| 48 |
+
"summary_activation": null,
|
| 49 |
+
"summary_first_dropout": 0.0,
|
| 50 |
+
"summary_proj_to_labels": true,
|
| 51 |
+
"summary_type": "cls_index",
|
| 52 |
+
"summary_use_proj": true,
|
| 53 |
+
"torch_dtype": "float32",
|
| 54 |
+
"transformers_version": "4.54.1",
|
| 55 |
+
"type_vocab_size": 2,
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"use_flash_attn": true,
|
| 58 |
+
"use_rms_norm": false,
|
| 59 |
+
"use_xentropy": true,
|
| 60 |
+
"vocab_size": 30528
|
| 61 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "5.1.0",
|
| 4 |
+
"transformers": "4.54.1",
|
| 5 |
+
"pytorch": "2.7.1"
|
| 6 |
+
},
|
| 7 |
+
"model_type": "SentenceTransformer",
|
| 8 |
+
"prompts": {
|
| 9 |
+
"query": "",
|
| 10 |
+
"document": ""
|
| 11 |
+
},
|
| 12 |
+
"default_prompt_name": null,
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
config_setfit.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"normalize_embeddings": false,
|
| 3 |
+
"labels": [
|
| 4 |
+
"addAsset",
|
| 5 |
+
"addAssetsUIAction",
|
| 6 |
+
"addText",
|
| 7 |
+
"align",
|
| 8 |
+
"applyAnimationObjectPreset",
|
| 9 |
+
"applyPageLevelAnimation",
|
| 10 |
+
"changeContentInImage",
|
| 11 |
+
"delete",
|
| 12 |
+
"displayHelpQA",
|
| 13 |
+
"distributeAroundObject",
|
| 14 |
+
"duplicatePage",
|
| 15 |
+
"duplicateSceneNode",
|
| 16 |
+
"duplicateSceneNodeToPage",
|
| 17 |
+
"fixTypography",
|
| 18 |
+
"flip",
|
| 19 |
+
"generateImageFromText",
|
| 20 |
+
"generateTemplates",
|
| 21 |
+
"group",
|
| 22 |
+
"moveRelativeTo",
|
| 23 |
+
"previewFilterEffects",
|
| 24 |
+
"proposeAssets",
|
| 25 |
+
"redo",
|
| 26 |
+
"removeBackground",
|
| 27 |
+
"removeContentFromImage",
|
| 28 |
+
"replaceAsset",
|
| 29 |
+
"replaceText",
|
| 30 |
+
"resetImageSettings",
|
| 31 |
+
"resize",
|
| 32 |
+
"resizePage",
|
| 33 |
+
"rotate",
|
| 34 |
+
"scatter",
|
| 35 |
+
"select",
|
| 36 |
+
"setBackgroundColor",
|
| 37 |
+
"setBlendMode",
|
| 38 |
+
"setBlur",
|
| 39 |
+
"setBorderStyle",
|
| 40 |
+
"setBrightness",
|
| 41 |
+
"setChildIndex",
|
| 42 |
+
"setContrast",
|
| 43 |
+
"setCropShape",
|
| 44 |
+
"setDropShadow",
|
| 45 |
+
"setFillColor",
|
| 46 |
+
"setFontSize",
|
| 47 |
+
"setFontStyle",
|
| 48 |
+
"setFontType",
|
| 49 |
+
"setHighlight",
|
| 50 |
+
"setImageAsBackground",
|
| 51 |
+
"setLetterSpacing",
|
| 52 |
+
"setLineSpacing",
|
| 53 |
+
"setOpacity",
|
| 54 |
+
"setParagraphSpacing",
|
| 55 |
+
"setSaturation",
|
| 56 |
+
"setShadow",
|
| 57 |
+
"setSharpness",
|
| 58 |
+
"setTextAlignment",
|
| 59 |
+
"setTextDecorationEffect",
|
| 60 |
+
"setTextLayout",
|
| 61 |
+
"setTextListStyle",
|
| 62 |
+
"setTextShadow",
|
| 63 |
+
"setWarmth",
|
| 64 |
+
"showUploadUI",
|
| 65 |
+
"undo",
|
| 66 |
+
"ungroup"
|
| 67 |
+
]
|
| 68 |
+
}
|
configuration_hf_nomic_bert.py
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import GPT2Config
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
class NomicBertConfig(GPT2Config):
|
| 5 |
+
model_type = "nomic_bert"
|
| 6 |
+
|
| 7 |
+
def __init__(
|
| 8 |
+
self,
|
| 9 |
+
prenorm=False,
|
| 10 |
+
parallel_block=False,
|
| 11 |
+
parallel_block_tied_norm=False,
|
| 12 |
+
rotary_emb_fraction=0.0,
|
| 13 |
+
fused_dropout_add_ln=False,
|
| 14 |
+
fused_bias_fc=False,
|
| 15 |
+
use_flash_attn=False,
|
| 16 |
+
use_xentropy=False,
|
| 17 |
+
qkv_proj_bias=True,
|
| 18 |
+
rotary_emb_base=10_000,
|
| 19 |
+
rotary_emb_scale_base=None,
|
| 20 |
+
rotary_emb_interleaved=False,
|
| 21 |
+
mlp_fc1_bias=True,
|
| 22 |
+
mlp_fc2_bias=True,
|
| 23 |
+
use_rms_norm=False,
|
| 24 |
+
causal=False,
|
| 25 |
+
type_vocab_size=2,
|
| 26 |
+
dense_seq_output=True,
|
| 27 |
+
pad_vocab_size_multiple=1,
|
| 28 |
+
tie_word_embeddings=True,
|
| 29 |
+
rotary_scaling_factor=None,
|
| 30 |
+
max_trained_positions=2048,
|
| 31 |
+
**kwargs,
|
| 32 |
+
):
|
| 33 |
+
self.prenorm = prenorm
|
| 34 |
+
self.parallel_block = parallel_block
|
| 35 |
+
self.parallel_block_tied_norm = parallel_block_tied_norm
|
| 36 |
+
self.rotary_emb_fraction = rotary_emb_fraction
|
| 37 |
+
self.tie_word_embeddings = tie_word_embeddings
|
| 38 |
+
self.fused_dropout_add_ln = fused_dropout_add_ln
|
| 39 |
+
self.fused_bias_fc = fused_bias_fc
|
| 40 |
+
self.use_flash_attn = use_flash_attn
|
| 41 |
+
self.use_xentropy = use_xentropy
|
| 42 |
+
self.qkv_proj_bias = qkv_proj_bias
|
| 43 |
+
self.rotary_emb_base = rotary_emb_base
|
| 44 |
+
self.rotary_emb_scale_base = rotary_emb_scale_base
|
| 45 |
+
self.rotary_emb_interleaved = rotary_emb_interleaved
|
| 46 |
+
self.mlp_fc1_bias = mlp_fc1_bias
|
| 47 |
+
self.mlp_fc2_bias = mlp_fc2_bias
|
| 48 |
+
self.use_rms_norm = use_rms_norm
|
| 49 |
+
self.causal = causal
|
| 50 |
+
self.type_vocab_size = type_vocab_size
|
| 51 |
+
self.dense_seq_output = dense_seq_output
|
| 52 |
+
self.pad_vocab_size_multiple = pad_vocab_size_multiple
|
| 53 |
+
self.rotary_scaling_factor = rotary_scaling_factor
|
| 54 |
+
self.max_trained_positions = max_trained_positions
|
| 55 |
+
|
| 56 |
+
super().__init__(**kwargs)
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa9aadd2159de2c42651146a5986764684ab69bce27981e785e6526cc9029108
|
| 3 |
+
size 546938168
|
model_head.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c2fcf5c85e55b03ddb9686e88e2cab24fd04e6aec17e2fa0af1333caca47794
|
| 3 |
+
size 388927
|
modeling_hf_nomic_bert.py
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
modules.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
}
|
| 14 |
+
]
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 8192,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 8192,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|