RecommendersText

HLLM

A two-level design: one language model reads the item description, the second builds the shopper interest from history. Ready checkpoints at 1B and 7B are published, but they need fine-tuning for your own catalogue.

Developer
ByteDance, China
First release
Sep 2024
Latest release
Aug 2025
Sizes
1B, 7B
License
Commercial use with conditionsApache 2.0 on the weights card; some builds are trained on top of Baichuan2, which has its own licence
Russian
Not stated
Running
On your own serverNeeds a GPU
Industries
Retail and marketplaces, Media and production, Marketing and content
Deploy on your server Hugging Face GitHub

What it does

  • Recommendations from browsing and purchase history
  • Understanding an item from its title and description
  • Suggesting cards for new items with no statistics
  • Personalised titles and captions for cards

Where it is used

Online stores and marketplacesContent platformsAdvertising and promotion

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. HLLM-Creator: персональные тексты к карточкам
  2. HLLM-1B и HLLM-7B (наборы Books и Pixel8M)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can HLLM be used in a commercial project?

With conditions. License: Apache 2.0 on the weights card; some builds are trained on top of Baichuan2, which has its own licence. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does HLLM need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does HLLM support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download HLLM and what does it cost?

The HLLM weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

RecommendersOneRec (OpenOneRec)Kuaishou · ChinaCommercial use allowed

An open foundation model for recommendations from a short-video service: browsing and purchase history is fed to the model as a sequence and it predicts the next item or clip. Fine-tuning on your own data is required.

DetailsRecommendersRecGPTVinAI Research · VietnamNon-commercial only

A 7B language model further trained on review and product-card text for recommendation and rating-prediction tasks. The licence forbids commercial use; a store still needs its own order history.

DetailsRecommendersMiniOneRecMiniOneRec open project · ChinaCommercial use allowed

A small open generative recommender at 1.5B with published checkpoints and a full training pipeline. Handy as a learning and starter option; a real store needs fine-tuning on its own orders.

Details

Source: huggingface.co/ByteDance/HLLM. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.