Instructions to use tobijen/bart_left_fulltext_torch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tobijen/bart_left_fulltext_torch with Transformers:

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

pipe = pipeline("text-generation", model="tobijen/bart_left_fulltext_torch")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tobijen/bart_left_fulltext_torch")
model = AutoModelForCausalLM.from_pretrained("tobijen/bart_left_fulltext_torch")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tobijen/bart_left_fulltext_torch with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tobijen/bart_left_fulltext_torch

SGLang

How to use tobijen/bart_left_fulltext_torch 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 "tobijen/bart_left_fulltext_torch" \
    --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": "tobijen/bart_left_fulltext_torch",
		"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 "tobijen/bart_left_fulltext_torch" \
        --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": "tobijen/bart_left_fulltext_torch",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tobijen/bart_left_fulltext_torch with Docker Model Runner:
```
docker model run hf.co/tobijen/bart_left_fulltext_torch
```

bart_left_fulltext_torch

This model is a fine-tuned version of facebook/bart-large on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.9329

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: 2e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	8	9.2222
No log	2.0	16	8.1910
No log	3.0	24	7.8851
No log	4.0	32	7.5382
No log	5.0	40	7.2200
No log	6.0	48	6.7294
No log	7.0	56	6.1038
No log	8.0	64	5.5721
No log	9.0	72	5.1404
No log	10.0	80	4.4875
No log	11.0	88	3.8785
No log	12.0	96	3.3749
No log	13.0	104	2.9965
No log	14.0	112	2.6608
No log	15.0	120	2.3879
No log	16.0	128	2.2349
No log	17.0	136	2.0993
No log	18.0	144	2.0023
No log	19.0	152	1.9480
No log	20.0	160	1.9329

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.14.1
Tokenizers 0.13.3

Downloads last month: 4

Model tree for tobijen/bart_left_fulltext_torch

Base model

facebook/bart-large

Finetuned

(197)

this model