Instructions to use rausch/en-t5-sci-continued-pretraining-487k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rausch/en-t5-sci-continued-pretraining-487k with Transformers:

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

pipe = pipeline("text-generation", model="rausch/en-t5-sci-continued-pretraining-487k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("rausch/en-t5-sci-continued-pretraining-487k")
model = AutoModelForSeq2SeqLM.from_pretrained("rausch/en-t5-sci-continued-pretraining-487k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rausch/en-t5-sci-continued-pretraining-487k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rausch/en-t5-sci-continued-pretraining-487k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rausch/en-t5-sci-continued-pretraining-487k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rausch/en-t5-sci-continued-pretraining-487k

SGLang

How to use rausch/en-t5-sci-continued-pretraining-487k 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 "rausch/en-t5-sci-continued-pretraining-487k" \
    --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": "rausch/en-t5-sci-continued-pretraining-487k",
		"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 "rausch/en-t5-sci-continued-pretraining-487k" \
        --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": "rausch/en-t5-sci-continued-pretraining-487k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rausch/en-t5-sci-continued-pretraining-487k with Docker Model Runner:
```
docker model run hf.co/rausch/en-t5-sci-continued-pretraining-487k
```

en-t5-sci-continued-pretraining-487k / conversion_info.json

root

Initial release with Git LFS

c83a6d9 10 months ago

Raw

History Blame Contribute Delete

1.62 kB

	{
	"source_path": "pretraining_logs_lr_001_OPTIMIZED_clean_restart/train/runs/2025-09-08_02-33-22/checkpoints/best/step-487500-val_ppl-3.72168.ckpt",
	"file_size_mb": 852.6802940368652,
	"analysis_time": "2025-11-17T23:42:54.899686",
	"global_step": 487500,
	"epoch": 0,
	"lightning_version": "2.5.1.post0",
	"step_from_filename": 487500,
	"learning_rate": 0.001,
	"model_name": "green-run-optimized-t5-base-sci-cp-en-487k-steps-lr0001-clip1",
	"batch_size": null,
	"run_info": {
	"run_name": "green-run-optimized",
	"run_type": "green-optimized",
	"base_model": "t5-base",
	"base_model_hf": "t5-base",
	"learning_rate": 0.001,
	"gradient_clip": 1.0,
	"scheduler": "inverse_sqrt",
	"warmup_steps": 20000,
	"config_name": "t5_continued_pretraining_lr_001_OPTIMIZED_clean_restart.yaml",
	"full_name_template": "green-run-optimized-t5-base-sci-cp-en-{steps}k-steps-lr0001-clip1"
	},
	"base_model": "t5-base",
	"training_type": "continued_pretraining",
	"gradient_clip": 1.0,
	"scheduler": "inverse_sqrt",
	"warmup_steps": 20000,
	"config_name": "t5_continued_pretraining_lr_001_OPTIMIZED_clean_restart.yaml",
	"analysis_error": "could not convert string to float: '3.72168.'",
	"conversion_time": "2025-11-17T23:43:06.934716",
	"output_path": "converted_models/hf_release/en-t5-sci-continued-pretraining-487k/green-optimized-run-models/green-run-optimized-t5-base-sci-cp-en-487k-steps-lr0001-clip1",
	"base_model_id": "t5-base",
	"base_model_used": "/netscratch/nrauscher/projects/BA-hydra/converted_models/baselines/t5-base",
	"missing_keys": 0,
	"unexpected_keys": 0
	}