Instructions to use vngrs/VBART-XLarge-Paraphrasing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vngrs/VBART-XLarge-Paraphrasing with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="vngrs/VBART-XLarge-Paraphrasing")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("vngrs/VBART-XLarge-Paraphrasing")
model = AutoModelForSeq2SeqLM.from_pretrained("vngrs/VBART-XLarge-Paraphrasing", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vngrs/VBART-XLarge-Paraphrasing with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vngrs/VBART-XLarge-Paraphrasing"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vngrs/VBART-XLarge-Paraphrasing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vngrs/VBART-XLarge-Paraphrasing

SGLang

How to use vngrs/VBART-XLarge-Paraphrasing with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "vngrs/VBART-XLarge-Paraphrasing" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vngrs/VBART-XLarge-Paraphrasing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "vngrs/VBART-XLarge-Paraphrasing" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vngrs/VBART-XLarge-Paraphrasing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vngrs/VBART-XLarge-Paraphrasing with Docker Model Runner:
```
docker model run hf.co/vngrs/VBART-XLarge-Paraphrasing
```

erdiari commited on Mar 18, 2024

Commit

15b63a3

verified ·

1 Parent(s): a1cf0bf

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -5

README.md CHANGED Viewed

@@ -54,7 +54,7 @@ The fine-tuning dataset is a mixture of [OpenSubtitles](https://huggingface.co/d
 This model is fine-tuned for paraphrasing tasks and finetuned in sentence level only. It is not intended to be used in any other case and can not be fine-tuned to any other task with full performance of the base model. It is also not guaranteed that this model will work without specified prompts.
 ### Training Procedure
-Pre-trained for 30 days and for a total of 708B tokens. Finetuned for 25 epoch.
 #### Hardware
 - **GPUs**: 8 x Nvidia A100-80 GB
 #### Software
@@ -65,17 +65,18 @@ Pre-trained for 30 days and for a total of 708B tokens. Finetuned for 25 epoch.
 - **Training objective**: Sentence permutation and span masking (using mask lengths sampled from Poisson distribution λ=3.5, masking 30% of tokens)
 - **Optimizer** : Adam optimizer (β1 = 0.9, β2 = 0.98, Ɛ = 1e-6)
 - **Scheduler**: Custom scheduler from the original Transformers paper (20,000 warm-up steps)
-- **Dropout**: 0.1 (dropped to 0.05 and then to 0 in the last 165k and 205k steps, respectively)
 - **Initial Learning rate**: 5e-6
-- **Training tokens**: 708B
 ##### Fine-tuning
 - **Training regime:** fp16 mixed precision
 - **Optimizer** : Adam optimizer (β1 = 0.9, β2 = 0.98, Ɛ = 1e-6)
 - **Scheduler**: Linear decay scheduler
 - **Dropout**: 0.1
--  **Learning rate**: 1e-5
--  **Fine-tune epochs**: 25
 #### Metrics
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62f8b3c84588fe31f435a92b/nrM_FA3bGk9NAYW_044HW.png)

 This model is fine-tuned for paraphrasing tasks and finetuned in sentence level only. It is not intended to be used in any other case and can not be fine-tuned to any other task with full performance of the base model. It is also not guaranteed that this model will work without specified prompts.
 ### Training Procedure
+Pre-trained for 8 days and for a total of 84B tokens. Finetuned for 25 epoch.
 #### Hardware
 - **GPUs**: 8 x Nvidia A100-80 GB
 #### Software
 - **Training objective**: Sentence permutation and span masking (using mask lengths sampled from Poisson distribution λ=3.5, masking 30% of tokens)
 - **Optimizer** : Adam optimizer (β1 = 0.9, β2 = 0.98, Ɛ = 1e-6)
 - **Scheduler**: Custom scheduler from the original Transformers paper (20,000 warm-up steps)
+- **Weight Initialization**: Model Enlargement from VBART-Large. See the related section in the [paper](https://arxiv.org/abs/2403.01308) for the details.
+- **Dropout**: 0.1 (dropped to 0.05 and then to 0 in the last 80K and 80k steps, respectively)
 - **Initial Learning rate**: 5e-6
+- **Training tokens**: 84B
 ##### Fine-tuning
 - **Training regime:** fp16 mixed precision
 - **Optimizer** : Adam optimizer (β1 = 0.9, β2 = 0.98, Ɛ = 1e-6)
 - **Scheduler**: Linear decay scheduler
 - **Dropout**: 0.1
+- **Learning rate**: 5e-6
+- **Fine-tune epochs**: 55
 #### Metrics
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62f8b3c84588fe31f435a92b/nrM_FA3bGk9NAYW_044HW.png)