Instructions to use youngermax/text-tagger-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use youngermax/text-tagger-v1 with Transformers:

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

pipe = pipeline("text-generation", model="youngermax/text-tagger-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("youngermax/text-tagger-v1")
model = AutoModelForCausalLM.from_pretrained("youngermax/text-tagger-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use youngermax/text-tagger-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/youngermax/text-tagger-v1

SGLang

How to use youngermax/text-tagger-v1 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 "youngermax/text-tagger-v1" \
    --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": "youngermax/text-tagger-v1",
		"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 "youngermax/text-tagger-v1" \
        --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": "youngermax/text-tagger-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use youngermax/text-tagger-v1 with Docker Model Runner:
```
docker model run hf.co/youngermax/text-tagger-v1
```

Model Details

Model Description

This model identifies multiple topics related to the text in natural language. It is finetuned on youngermax/text-tagging for 3.5 epoch over ~1.3 hours on a free Kaggle P100.

Developed by: Lincoln Maxwell
Model type: Generative Pretrained Transformer
Language(s) (NLP): English
Finetuned from model: DistilGPT2

Uses

Direct Use


input_ids = tokenizer.encode(prompt + '<|topic|>', return_tensors='pt').to('cuda')

# Generate text
output = model.generate(
  input_ids,
  max_length=1024,
  num_return_sequences=1,
  eos_token_id=tokenizer.eos_token_id,
  pad_token_id=tokenizer.eos_token_id,
  top_k=100,
  top_p=0.5,
  temperature=1
)

# Decode the output
text = tokenizer.decode(output[0], skip_special_tokens=False, early_stopping=True)
text = text[len(prompt):text.find('<|endoftext|>')]

topics = list(set(list(map(lambda x: x.strip(), text.split('<|topic|>')))[1:]))

Downloads last month: 3

Safetensors

Model size

81.9M params

Tensor type

F32

youngermax
/

text-tagger-v1

Model Details

Model Description

Uses

Direct Use

Dataset used to train youngermax/text-tagger-v1