Voicelab / text-generation updated 2 years ago

vlt5-base-keywords

Name: vlt5-base-keywords
Author: Voicelab

> Our vlT5 model is a keyword generation model based on encoder-decoder architecture using Transformer blocks presented by Google (https://huggingface.co/t5-base). The vlT5 was trained on scientific articles corpus to predict a given set of keyphrases based on the concatenation of the article’s abstract and title. It generates precise, yet not always complete keyphrases that describe the content of the article based...

Params

280 M

Context

—

Downloads 30d

221 K

Likes

Commercial use: allowed cc-by-4.0 Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

221 K182 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	1.1 GB	1.8 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/vlt5-base-keywords
{
  "hf_id": "Voicelab/vlt5-base-keywords",
  "params_b": 0.28,
  "context_length": null,
  "license": { "id": "cc-by-4.0", "commercial": "yes" },
  "downloads_30d": 220918,
  "vram_estimates": [
    { "quant": "f32", "gb": 1.8 }
  ],
  "updated_at": "2026-07-28T18:08:29Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: T5ForConditionalGeneration
Parameters: 280 M
Tensor type: F32
Vocabulary: 50,048
Licence: cc-by-4.0
First seen on the Hub: 2022-09-27
Training datasets: posmac
Added to our catalog: 2026-07-28

Compare with

Qwen3-0.6B 29.7 M gpt2 13.7 M Qwen2.5-0.5B-Instruct 6.6 M Qwen2.5-0.5B 2.6 M pythia-160m 2.5 M gemma-3-270m 2.1 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB