The IndexGuidesNews
AboutContribute

Parameter descriptions:

Base Model Data
Are datasources for training the base model comprehensively documented and freely made available? In case a distinction between base (foundation) and end (user) model is not applicable, this mirrors the end model data entries.
End User Model Data
Are datasources for training the model that the enduser interacts with comprehensively documented and freely made available?
Base Model Weights
Are the weights of the base models made freely available? In case a distinction between base (foundation) and end (user) model is not applicable, this mirrors the end model data entries.
End User Model Weights
Are the weights of the model that the enduser interacts with made freely available?
Training Code
Is the source code of datasource processing, model training and tuining comprehensively and freely made available?
Code Documentation
Is the source code of datasource processing, model training and tuning comprehensively documented?
Hardware Architecture
Is the hardware architecture used for datasource processing and model training comprehensively documented?
Preprint
Are archived preprint(s) are available that detail all major parts of the system including datasource processing, model training and tuning steps?
Paper
Are peer-reviewed scientific publications available that detail all major parts of the system including datasource processing, model training and tuning steps?
Modelcard
Is a model card in standardized format available that provides comprehensive insight on model architecture, training, fine-tuning, and evaluation are available?
Datasheet
Is a datasheet as defined in "Datasheets for Datasets" (Gebru et al. 2021) available?
Package
Is a packaged release of the model available on a software repository (e.g. a Python Package Index, Homebrew)?
API and Meta Prompts
Is an API available that provides unrestricted access to the model (other than security and CDN restrictions)? If applicable, this entry also collects information on the use and availability of meta prompts.
Licenses
Is the project fully covered by Open Source Initiative (OSI)-approved licenses, including all data sources and training pipeline code?

BELLE

by KE Technologies

Llama-2 fine-tuned on a small amount of Chinese data.
Text
Limited
https://huggingface.co/BELLE-2/BELLE-Llama2-13B-chat-0.4M
Llama-2-13B
BELLE-Llama2-13B-Chat-0.4M
Apache License 2.0
Company specializing in advanced technology solutions.
http://www.ke.com
March 2023
Availability
Training Code
Repository contains a fair bit of code
https://github.com/LianjiaTech/BELLE
Base Model Data
Open for variants based on BLOOMZ. Closed for variants based on LLaMA, whose pretraining data is nowhere disclosed or documented.
End User Model Data
Synthetic BELLE training data in Chinese released in batches
https://github.com/LianjiaTech/BELLE/tree/main/data/1.5M
Base Model Weights
LLaMA based but copyright status unclear
End User Model Weights
Some models available, most only as delta weights requiring separate access to LLaMA
https://github.com/LianjiaTech/BELLE/tree/main/models
Documentation
Code Documentation
Quite some documentation on Github, though not all well-organized
https://github.com/LianjiaTech/BELLE/blob/main/README_en.md
Hardware Architecture
Specified in a fair bit of detail on github
https://github.com/LianjiaTech/BELLE/blob/main/README_en.md
Preprint
https://arxiv.org/abs/2303.14742
Paper
No peer-reviewed paper found
Modelcard
Provide model cards for various BELLE models on their Huggingface page; most are not fully detailed and are missing certain aspects e.g. hyperparameters.
https://huggingface.co/BelleGroup
Datasheet
No data sheet found
Access
Package
No dedicated package available
API and Meta Prompts
No API found
Licenses
Lowest common denominator is non-OSI approved LLaMA licence agreement
Is this information not up to date?
Contribute here ->

Supported by the Centre for Language Studies and the Dutch Research Council. Website design & development © 2024 by BSTN. This version of the index generated 09 Apr 2025, website content last updated 23 Apr 2025.