Usage
from transformers import pipeline
# load model and tokenizer from huggingface hub with pipeline
enhancer = pipeline("summarization", model="gokaygokay/Lamini-Prompt-Enchance-Long", device=0)
prompt = "A blue-tinted bedroom scene, surreal and serene, with a mysterious reflected interior."
prefix = "Enhance the description: "
# enhance prompt
res = enhancer(prefix + prompt)
print(res[0]['summary_text'])
Lamini-Prompt-Enchance-Long
This model is a fine-tuned version of MBZUAI/LaMini-Flan-T5-248M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1624
- Rouge1: 20.2443
- Rouge2: 9.3642
- Rougel: 17.2484
- Rougelsum: 19.0703
- Gen Len: 19.0
Model description
More information needed
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.4435 | 1.0 | 2014 | 2.2723 | 20.0108 | 9.2736 | 17.0569 | 18.8171 | 19.0 |
| 2.341 | 2.0 | 4028 | 2.2120 | 20.4422 | 9.4473 | 17.4347 | 19.2234 | 19.0 |
| 2.2948 | 3.0 | 6042 | 2.1820 | 20.5645 | 9.5426 | 17.5419 | 19.3714 | 19.0 |
| 2.2598 | 4.0 | 8056 | 2.1668 | 20.2354 | 9.3639 | 17.2379 | 19.0625 | 19.0 |
| 2.2431 | 5.0 | 10070 | 2.1624 | 20.2443 | 9.3642 | 17.2484 | 19.0703 | 19.0 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 568
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.
Model tree for gokaygokay/Lamini-Prompt-Enchance-Long
Base model
MBZUAI/LaMini-Flan-T5-248M