|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- samsum |
|
language: |
|
- en |
|
library_name: transformers |
|
tags: |
|
- peft |
|
- lora |
|
- t5 |
|
- flan |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-t5-xxl-samsum-peft |
|
results: |
|
- task: |
|
name: Sequence-to-sequence Language Modeling |
|
type: text2text-generation |
|
dataset: |
|
name: samsum |
|
type: samsum |
|
config: samsum |
|
split: train |
|
args: samsum |
|
metrics: |
|
- name: Rouge1 |
|
type: rouge |
|
value: 50.386161 |
|
--- |
|
|
|
# FLAN-T5-XXL LoRA fine-tuned on `samsum` |
|
|
|
PEFT tuned FLAN-T5 XXL model. |
|
|
|
|
|
# flan-t5-base-samsum |
|
|
|
This model is a fine-tuned version of [philschmid/flan-t5-xxl-sharded-fp16](https://huggingface.co/philschmid/flan-t5-xxl-sharded-fp16) on the samsum dataset. |
|
It achieves the following results on the evaluation set: |
|
|
|
- rogue1: 50.386161% |
|
- rouge2: 24.842412% |
|
- rougeL: 41.370130% |
|
- rougeLsum: 41.394230% |
|
|
|
- |
|
|
|
## How to use the model |
|
|
|
The model was trained using 🤗 [PEFT](https://github.com/huggingface/peft). This repository only contains the fine-tuned adapter weights for LoRA and the configuration to load the model. Below you can find a snippet on how to run inference using the model. This will load the FLAN-T5-XXL from hugging face if not existing locally. |
|
|
|
1. load the model |
|
|
|
```python |
|
import torch |
|
from peft import PeftModel, PeftConfig |
|
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer |
|
|
|
# Load peft config for pre-trained checkpoint etc. |
|
peft_model_id = "philschmid/flan-t5-xxl-samsum-peft" |
|
config = PeftConfig.from_pretrained(peft_model_id) |
|
|
|
# load base LLM model and tokenizer |
|
model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path, load_in_8bit=True, device_map={"":0}) |
|
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path) |
|
|
|
# Load the Lora model |
|
model = PeftModel.from_pretrained(model, peft_model_id, device_map={"":0}) |
|
model.eval() |
|
``` |
|
|
|
2. generate |
|
```python |
|
|
|
text = "test" |
|
|
|
input_ids = tokenizer(text, return_tensors="pt", truncation=True).input_ids.cuda() |
|
outputs = model.generate(input_ids=input_ids, max_new_tokens=10, do_sample=True, top_p=0.9) |
|
print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0]) |
|
``` |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 1e-3 |
|
- train_batch_size: auto |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.1 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.9.1 |
|
- PEFT@main |
