Instructions to use alpeshsonar/lot-t5-small-filter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alpeshsonar/lot-t5-small-filter with Transformers:

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

pipe = pipeline("text-generation", model="alpeshsonar/lot-t5-small-filter")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("alpeshsonar/lot-t5-small-filter")
model = AutoModelForSeq2SeqLM.from_pretrained("alpeshsonar/lot-t5-small-filter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alpeshsonar/lot-t5-small-filter with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/alpeshsonar/lot-t5-small-filter

SGLang

How to use alpeshsonar/lot-t5-small-filter 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 "alpeshsonar/lot-t5-small-filter" \
    --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": "alpeshsonar/lot-t5-small-filter",
		"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 "alpeshsonar/lot-t5-small-filter" \
        --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": "alpeshsonar/lot-t5-small-filter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alpeshsonar/lot-t5-small-filter with Docker Model Runner:
```
docker model run hf.co/alpeshsonar/lot-t5-small-filter
```

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

Uses

from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("alpeshsonar/lot-t5-small-filter")
model = T5ForConditionalGeneration.from_pretrained("alpeshsonar/lot-t5-small-filter")

input_text = """"Extract lots from given text.
* age ≥18 years * patients with de novo or secondary AML, with an unfavorable or intermediate karyotype (according to the 2017 ELN classification), or patients with relapsing AML who may receive second-line treatment * not candidates for intensive induction, for the following reasons* 75 years or ≥ 18 to 74 years and at least one of the following comorbidities: PS ≥ 2 or a history of heart failure requiring treatment or LVEF ≤ 50% or chronic stable angina or FEV1 ≤ 65% or DLCO ≤ 65% or creatinine clearance <45 ml / min; or liver damage with total bilirubin> 1.5 N or other comorbidities that the hematologist considers incompatible with intensive treatment * ineligible for a classic allogeneic hematopoietic stem cell transplant due to the presence of co-morbidities or too high a risk of toxicity >70 years old or at least one of the following comorbidities: PS ≥ 2 or a history of heart failure requiring treatment or LVEF ≤ 50% or chronic stable angina or FEV1 ≤ 65% or DLCO ≤ 65% or creatinine clearance <45 ml / min; or liver damage with total bilirubin> 1.5 N * may receive chemotherapy with hypomethylating agents have a partially compatible (haplo-identical) major family donor (≥18 years old) eligible for lymphocyte donation.
"""
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
outputs = model.generate(input_ids,max_new_tokens=1024)
print(tokenizer.decode(outputs[0],skip_special_tokens=True))

Downloads last month: 11

Safetensors

Model size

60.5M params

Tensor type

BF16

Model tree for alpeshsonar/lot-t5-small-filter

Base model

google-t5/t5-small

Finetuned

(2320)

this model

alpeshsonar
/

lot-t5-small-filter

Uses

Model tree for alpeshsonar/lot-t5-small-filter

Space using alpeshsonar/lot-t5-small-filter 1