timm provides PyTorch image encoders and backbones along with training, evaluation, inference, and export scripts.
Open source
24 alternativesAlpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
About Alpaca
Stanford Alpaca is a GitHub repository providing code and documentation for training instruction-following LLaMA models and generating the underlying data. It contains 52K instruction-following examples, scripts for generating that data using techniques from the Self-Instruct paper, fine-tuning code, seed tasks and prompt templates, plus a weight diff script for recovering Alpaca-7B weights.
Use is deliberately restricted. The project is licensed for research use only, the dataset and weight diff are CC BY NC 4.0 (non-commercial use only), and models trained with the dataset should not be used outside research. The live demo is suspended until further notice, the model was not fine-tuned to be safe or harmless, and the project states it is still under development with limitations to address. In a preliminary human evaluation, the Alpaca 7B model behaved similarly to text-davinci-003 on the Self-Instruct evaluation suite.
Key features
- 52K instruction-following examples in alpaca_data.json
- Scripts for generating instruction data via Self-Instruct techniques
- Fine-tuning code for the Alpaca model
- Script to recover Alpaca-7B weights from the weight diff
- Seed tasks and prompt templates for training and inference
- Datasheet and model card documentation included
Best for: Machine learning researchers studying instruction-following model training who can work within a research-only, non-commercial license.
Good for
- Open-source release of data generation procedure, dataset and training recipe
- Dataset and weight diff carry explicit CC BY NC 4.0 license terms
- Includes a datasheet and model card alongside the code
Watch out for
- Licensed for research use only, with non-commercial limits on the dataset and weight diff
- Model was not fine-tuned to be safe or harmless and remains under development
- Live demo is suspended until further notice
Alpaca at a glance
- Category
- AI & Machine Learning › Models & ML Research
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Alpaca alternatives
Tools and sites you could use instead, ranked by how closely they match.
CodeGen provides open-source models for program synthesis and code generation.
Open source
24 alternatives
DeepSeek Coder is a language model project for code generation and programming tasks.
Open source
24 alternatives
This repository contains Google Research code for the Flan-T5 language model project.
Open source
24 alternatives
MobiLlama is a small language model designed for edge devices, according to its repository description.
Open source
24 alternatives
Janus combines multimodal understanding and image generation models in a unified model series.
Open source
24 alternativesPopular in Models & ML Research
Well-known listings from the same topic.
Falcon LLMfalconllm.tii.aeERNIEernie.baidu.comTokenVersetoken-verse.github.iowTAObittensor.comAlpacacrfm.stanford.edu/2023/03/13/alpaca.htmlSmolVLAhuggingface.co/blog/smolvla
Alpaca FAQ
Can Alpaca or its data be used commercially?
No. The project is intended and licensed for research use only, and the dataset and weight diff are CC BY NC 4.0, allowing only non-commercial use.
Is the Alpaca live demo available?
No. The repository states the live demo is suspended until further notice.
What model is Alpaca based on and how was it trained?
The Alpaca model is fine-tuned from a 7B LLaMA model on 52K instruction-following examples generated using Self-Instruct techniques with some modifications.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.