Alpaca
Stanford · March 2023
● activeOpen Sourcedecoder onlytext
Parameters7B
Why It Matters
Proved that fine-tuning an open model on synthetic instruction data could replicate much of ChatGPT's conversational ability for under $600, sparking a wave of community-driven model development.
Description
Stanford's instruction-tuned version of LLaMA that demonstrated you could create a ChatGPT-like model for under $600. Fine-tuned on 52K instruction-following examples generated by GPT-3.5, it proved that high-quality instruction tuning data matters more than model scale for conversational ability.
Key Innovations
Instruction Tuning
Instruction TuningFine-tuning a model on instruction-response pairs so it follows user commands more reliably.
Distillation
DistillationTraining a smaller 'student' model to mimic a larger 'teacher' model, preserving capability at lower cost.
More from Community / Uncensored
WizardLM2023-06 · 13B
Dolphin (Eric Hartford)2023-07 · —
Hermes (Nous Research)2023-09 · —
LLaMA 4 Scout Abliterated2025-05 · 81B (17B active × 16 experts)
DeepSeek R1 Uncensored2025-03 · 671B (37B active)
Bark2023-04 · —
Mistral 7B Uncensored2024-01 · 7B
Qwen 2.5 72B Abliterated2025-01 · 72B
SOLAR 10.7B Uncensored2024-02 · 10.7B
LLaMA 3.1 405B Abliterated2024-08 · 405B