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?

StableVicuna

by CarperAI

StableVicuna-13B is a Vicuna-13B v0 model fine-tuned using reinforcement learning from human feedback (RLHF) via Proximal Policy Optimization (PPO) on various conversational and instructional datasets
Text
Full
https://huggingface.co/CarperAI/stable-vicuna-13b-delta
LLaMA
OASST1 (human), GPT4All (human), Alpaca (synthetic)
Meta Community License
CarperAI, an AI research team spun out of EleutherAI.
https://carper.ai
April 2023
Availability
Training Code
Training code not made public, only code for applying the delta.
Base Model Data
Based on LLaMA whose pretraining data has nowhere been disclosed or documented.
https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md#training-dataset
End User Model Data
From the documentation 'The reward model used during RLHF was also trained on OpenAssistant Conversations Dataset (OASST1) along with two other datasets Anthropic HH-RLHF, a dataset of preferences about AI assistant helpfulness and harmlessness; and Stanford Human Preferences Dataset a dataset of 385K collective human preferences over responses to questions/instructions in 18 different subject areas, from cooking to legal advice.'
https://huggingface.co/CarperAI/stable-vicuna-13b-delta
Base Model Weights
Based on LLaMA weights, which are not openly available though a leaked versions is in wide circulation.
End User Model Weights
Model not functional out of the box as weights require a delta computation. From the docs 'StableVicuna-13B cannot be used from the CarperAI/stable-vicuna-13b-delta weights alone. To obtain the correct model, one must add back the difference between LLaMA 13B and CarperAI/stable-vicuna-13b-delta weights.'
https://huggingface.co/CarperAI/stable-vicuna-13b-delta#apply-delta-weights
Documentation
Code Documentation
Code is minimally documented and deployment requires non-trivial configuration, e.g. 'StableVicuna-13B cannot be used from the CarperAI/stable-vicuna-13b-delta weights alone. To obtain the correct model, one must add back the difference between LLaMA 13B and CarperAI/stable-vicuna-13b-delta weights.'
https://huggingface.co/CarperAI/stable-vicuna-13b-delta/tree/main
Hardware Architecture
Architecture is described at a high level in scattered places, but there is no clear and exhaustive overview.
Preprint
No preprint available.
Paper
No paper found.
Modelcard
Model card provides some information but is not fully worked out as recommended in model card literature.
https://huggingface.co/lmsys/vicuna-13b-delta-v0
Datasheet
No datasheet found
Access
Package
No package found
API and Meta Prompts
No API available.
Licenses
CC-BY-NC-SA-4.0. License for LLaMA is more murky, hence partial. As they say 'License for the base LLaMA model's weights is Meta's non-commercial bespoke license.'
https://huggingface.co/CarperAI/stable-vicuna-13b-delta
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.