Maintainer: stabilityai

Total Score


Last updated 5/28/2024


Model LinkView on HuggingFace
API SpecView on HuggingFace
Github LinkNo Github link provided
Paper LinkNo paper link provided

Get summaries of the top AI models delivered straight to your inbox:

Model overview

Stable LM 2 12B is a 12.1 billion parameter decoder-only language model developed by Stability AI. It was pre-trained on 2 trillion tokens of diverse multilingual and code datasets for two epochs. The model is part of the Stable LM 2 series, which also includes the Stable LM 2 1.6B and Stable Code 3B models. Compared to the smaller 1.6B version, the 12B model has significantly more parameters and demonstrates improved performance on various benchmarks.

Model inputs and outputs

The Stable LM 2 12B model is a text generation model that takes natural language prompts as input and generates coherent, contextual text output. The model can be used for a variety of natural language tasks, such as summarization, translation, and open-ended generation.


  • Natural language prompts in various languages, with a focus on English


  • Coherent, context-aware text generated in response to the input prompts
  • The model can generate text of varying lengths, from short phrases to multi-paragraph passages


The Stable LM 2 12B model demonstrates strong performance on a range of natural language tasks, including open-ended generation, summarization, and translation. It can be used to generate human-like text on a variety of topics, from creative writing to technical documentation. The model's large size and diverse training data allow it to capture a wide range of linguistic patterns and knowledge.

What can I use it for?

Stable LM 2 12B can be a powerful tool for developers and researchers working on natural language processing applications. Some potential use cases include:

  • Content generation: The model can be used to generate original text for applications like creative writing, article generation, and chatbots.
  • Summarization: The model can be fine-tuned to summarize longer passages of text, making it useful for tasks like document summarization.
  • Translation: The multilingual capabilities of the model can be leveraged for machine translation between supported languages.
  • Knowledge-based applications: The model's broad training data can be leveraged to build applications that require access to a wide range of information, such as question-answering systems.

However, as a large language model, Stable LM 2 12B may exhibit biases or generate unsafe content. Users should carefully evaluate the model's outputs and consider potential risks before deploying it in production systems.

Things to try

Some interesting things to try with Stable LM 2 12B include:

  • Experimenting with different prompting and generation strategies to explore the model's capabilities in areas like creative writing, task completion, and open-ended dialogue.
  • Fine-tuning the model on domain-specific datasets to adapt it for specialized applications, such as technical writing or customer service chatbots.
  • Combining the model with other AI components, such as vision models or recommender systems, to build more complex, multimodal applications.
  • Investigating the model's reasoning and knowledge capabilities by probing it with a variety of questions and tasks.

As with any powerful AI system, it's important to use Stable LM 2 12B responsibly and with appropriate safeguards in place. Continuous evaluation and refinement will be crucial to ensuring the model's outputs are safe, ethical, and aligned with user needs.

This summary was produced with help from an AI and may contain inaccuracies - check out the links to read the original source documents!

Related Models




Total Score


Stable LM 2 1.6B is a 1.6 billion parameter decoder-only language model developed by Stability AI. It was pre-trained on 2 trillion tokens of diverse multilingual and code datasets for two epochs. This model can be contrasted with similar large language models from Stability AI, such as stable-code-3b, which is focused on code generation, and stablelm-tuned-alpha-7b, which has been fine-tuned for chat-like applications. Model inputs and outputs Stable LM 2 1.6B is a text generation model that can be used to generate natural language text based on a given prompt. The model takes a text prompt as input and outputs a continuation or completion of that text. Inputs Text prompt**: A string of text that the model will use as the starting point for text generation. Outputs Generated text**: The model will generate new text that continues or extends the input prompt. The length and content of the generated text is controlled by parameters such as max_new_tokens, temperature, and top_p. Capabilities Stable LM 2 1.6B is a powerful language model that can be used for a variety of text generation tasks, such as writing, summarization, and translation. The model has been trained on a diverse corpus of data, giving it broad knowledge and the ability to generate coherent and contextually relevant text. Some key capabilities of the model include: Multilingual generation**: The model can generate text in multiple languages, not just English. Code generation**: The model has been trained on programming language data and can generate code snippets. Creative writing**: The model can be used to generate short stories, poems, and other creative writing. What can I use it for? Stable LM 2 1.6B can be used for a variety of applications, including: Content generation**: The model can be used to generate text for blogs, articles, social media posts, and other content. Summarization**: The model can be used to summarize long passages of text. Translation**: The model's multilingual capabilities can be used for translation between languages. Prototyping and ideation**: The model can be used to generate ideas and explore creative concepts. When using Stable LM 2 1.6B commercially, please refer to the Stability AI membership information. Things to try One interesting thing to try with Stable LM 2 1.6B is its capability for generating code. By providing the model with a prompt that includes instructions for a specific coding task, you can use the model to generate working code snippets. For example, you could prompt the model with "Write a Python function to find the number of CPU cores on a system" and see the model generate a functional code solution. Another interesting aspect of the model is its ability to generate multilingual text. You can experiment with prompts in different languages to see the model's performance across various linguistic domains. This could be useful for tasks like machine translation or developing multilingual chatbots and virtual assistants. Overall, Stable LM 2 1.6B is a versatile language model with a wide range of potential applications. By exploring its various capabilities and experimenting with different prompts and use cases, you can discover new and innovative ways to leverage this powerful AI technology.

Read more

Updated Invalid Date



Total Score


StableLM-3B-4E1T is a 3 billion parameter decoder-only language model developed by Stability AI. The model was pre-trained on 1 trillion tokens of diverse English and code datasets for 4 epochs. Similar models in the Stable LM collection include the Stable LM 2 12B and Stable LM 2 1.6B, which are 12.1 and 1.6 billion parameter models respectively, pre-trained on 2 trillion tokens. Model inputs and outputs StableLM-3B-4E1T is a text generation model that can be used to generate coherent and contextual text based on a given prompt. The model takes natural language text as input and outputs a continuation of the text. Inputs Natural language text prompts Outputs Continued text generated by the model, based on the input prompt Capabilities StableLM-3B-4E1T demonstrates strong performance on a variety of natural language processing tasks, including text generation, summarization, and question answering. The model is particularly adept at producing coherent and contextual text, making it well-suited for applications such as content creation, dialogue systems, and language-based AI assistants. What can I use it for? StableLM-3B-4E1T can be used as a foundational model for a wide range of natural language processing applications. For example, it could be fine-tuned for tasks like creative writing, code generation, or even chatbots and virtual assistants. The model's large scale and diverse pre-training dataset make it a powerful starting point for many language-based AI projects. Things to try One interesting aspect of StableLM-3B-4E1T is its ability to handle long-form text generation. By leveraging the 4,096 token sequence length, the model can produce coherent and contextual text that maintains a consistent narrative over an extended period. This capability could be particularly useful for applications like story generation, report writing, or even novel composition.

Read more

Updated Invalid Date




Total Score


StableLM 2 12B Chat is a 12 billion parameter instruction-tuned language model developed by Stability AI. It is trained on a mix of publicly available datasets and synthetic datasets, utilizing Direct Preference Optimization (DPO). This model is an evolution of the Stable LM 2 12B model, with additional fine-tuning to improve its conversational abilities. Model Inputs and Outputs StableLM 2 12B Chat uses a chat-style input format, where the user prompts are presented in the user role, and the model's responses are in the assistant role. This format is available through the tokenizer's apply_chat_template method. Inputs Conversational prompts in a chat-style format, with the user's message in the user role. Outputs Responses generated by the model, in the assistant role, continuing the conversation. The model can also support function calling, allowing users to request the generation of images or other outputs. Capabilities StableLM 2 12B Chat is capable of engaging in open-ended conversations, answering questions, and generating text on a wide range of topics. It has been further fine-tuned to improve its conversational abilities compared to the base Stable LM 2 12B model. What Can I Use It For? StableLM 2 12B Chat is well-suited for building conversational AI applications, such as chatbots, virtual assistants, or dialogue systems. Its ability to understand context and engage in back-and-forth conversations makes it a powerful tool for creating more natural and engaging user experiences. Things to Try One interesting aspect of StableLM 2 12B Chat is its support for function calling, which allows users to request specific outputs beyond just text generation, such as image creation. This opens up opportunities to build more interactive and multimodal applications that seamlessly integrate language and other capabilities.

Read more

Updated Invalid Date




Total Score


stable-code-3b is a 2.7B parameter decoder-only language model pre-trained on 1.3 trillion tokens of diverse textual and code datasets. Developed by Stability AI, stable-code-3b demonstrates state-of-the-art performance on the MultiPL-E metrics across multiple programming languages compared to models of similar size. It outperforms other code generation models like CodeLLama, Deepseek Coder, and Wizard Coder on tasks like Python, C++, and JavaScript. Model inputs and outputs stable-code-3b is a text-to-text model, taking in prompts as input and generating relevant code as output. It can handle long context, with the ability to generate code based on sequences up to 16,384 tokens. The model also supports a "Fill in Middle" (FIM) capability, where it can complete partially-written code snippets. Inputs Text prompts for code generation, up to 16,384 tokens Partial code snippets for the "Fill in Middle" capability Outputs Generated code in one of 18 programming languages the model was trained on, including Python, C++, JavaScript, Java, PHP, and Rust Capabilities stable-code-3b excels at generating high-quality, functional code across a variety of programming languages. It can be used to write entire programs from scratch, or fill in missing sections of existing code. The model's strong performance on the MultiPL-E benchmark suggests it can handle a wide range of coding tasks and produce code that is syntactically correct and logically sound. What can I use it for? stable-code-3b can be a valuable tool for developers, data scientists, and anyone working with code. It could be used to speed up prototyping and development by automatically generating boilerplate code or completing repetitive tasks. The model could also be fine-tuned on domain-specific datasets to create customized code generation models for specialized applications. Things to try Experiment with different prompting techniques to see how stable-code-3b responds. Try providing high-level descriptions of the functionality you want, or giving it partially-completed code snippets to fill in. You can also try adjusting parameters like temperature and top-k/top-p values during generation to control the creativity and diversity of the output. By exploring the model's capabilities, you can unlock new ways to streamline your coding workflows.

Read more

Updated Invalid Date