Context aware splitter 1.1b
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0598
Model description
- This model is used to split texts in a context aware way. Used for RAG applications.
- This model is based off TinyLLaMA 1.1b It uses the Alpaca format:
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
Your task is to segment text into smaller blocks. Split the text where it makes sense and be vary of the context. The ideal split should be close to {WORD_COUNT} words.
### Input:
Q: Information/File Manager I'm looking for a file manager application which helps to organize a large amount of movies, pictures, music, text documents, databases, audio-books and ebooks. Right now I only use the Finder which doesn't work well, because I really need a function to put single files into multiple categories. Simply using the file system for this creates a confusing nesting of files. A: Depending on the number of categories you require to handle, you could always use a combination of the finder with the built in label functionality, thus a movie can be held in one area (movies directory, for example), but "tagged" as something else. Using smart directories and saved searches you can view your files by a combination of the attributes (location, label, media type) to create custom views. All without purchasing software. Cheap and cheerful, but may be suitable to your needs. A: Maybe use a file manager that supports Open Meta. Or use symbolic links for organizing all your media files. Or even use hardlinked files if you dare.
### Response:
Response:
{'splits': ["Q: Information/File Manager I'm looking for a file manager application which helps to organize a large amount of movies, pictures, music, text documents, databases, audio-books and ebooks. Right now I only use the Finder which doesn't work well, because I really need a function to put single files into multiple categories. Simply using the file system for this creates a confusing nesting of files.", 'A: Depending on the number of categories you require to handle, you could always use a combination of the finder with the built in label functionality, thus a movie can be held in one area (movies directory, for example), but "tagged" as something else. Using smart directories and saved searches you can view your files by a combination of the attributes (location, label, media type) to create custom views. All without purchasing software. Cheap and cheerful, but may be suitable to your needs.', 'A: Maybe use a file manager that supports Open Meta. Or use symbolic links for organizing all your media files. Or even use hardlinked files if you dare.'], 'topic': 'Discussion on file manager applications for organizing large amount of media files.'}
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.9849 | 0.03 | 1 | 2.0811 |
1.3107 | 0.17 | 5 | 1.1992 |
0.6399 | 0.34 | 10 | 0.6359 |
0.2779 | 0.51 | 15 | 0.2862 |
0.1807 | 0.68 | 20 | 0.1634 |
0.1256 | 0.85 | 25 | 0.1177 |
0.097 | 1.0 | 30 | 0.0891 |
0.1063 | 1.17 | 35 | 0.0734 |
0.0769 | 1.34 | 40 | 0.0723 |
0.0694 | 1.51 | 45 | 0.0633 |
0.0687 | 1.69 | 50 | 0.0624 |
0.0575 | 1.86 | 55 | 0.0622 |
0.0516 | 2.01 | 60 | 0.0609 |
0.0582 | 2.18 | 65 | 0.0603 |
0.0611 | 2.35 | 70 | 0.0600 |
0.0515 | 2.52 | 75 | 0.0598 |
0.0704 | 2.69 | 80 | 0.0598 |
0.0525 | 2.86 | 85 | 0.0598 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 53
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.