The Open-Assistant Pythia SFT-4 (12B) is the fourth iteration of the English supervised fine-tuning (SFT) model developed by the Open-Assistant project. It is based on the Pythia 12B architecture and has been fine-tuned on human demonstrations of assistant conversations collected through the open-assistant.io human feedback web app.
The model is intended for use in various natural language processing tasks, particularly in creating AI assistants capable of engaging in human-like conversations, answering questions, and performing language-related tasks.Technical DetailsArchitecture
While specific performance metrics are not provided in the available information, the model is expected to perform well on assistant-like tasks due to its specialized training.
Code Sample
Users should be aware of potential biases in the model's outputs and use it responsibly, avoiding harmful or discriminatory applications.
The model is released under the Apache 2.0 license, which allows for both commercial and non-commercial use.
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Open-Assistant Pythia SFT-4 (12B) This page | ||||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Yes, Open-Assistant Pythia SFT-4 (12B) can stream responses as they are generated.
Yes, Open-Assistant Pythia SFT-4 (12B) supports both function calling and structured outputs.
Open-Assistant Pythia SFT-4 (12B) was built by OpenAssistant.
It uses the v1 endpoint.
