Maintainer: TheBloke

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

Create account to get full access


If you already have an account, we'll log you in

Model overview

The wizard-mega-13B-GPTQ model is a 13-billion parameter language model created by the Open Access AI Collective and quantized by TheBloke. It is an extension of the original Wizard Mega 13B model, with multiple quantized versions available to choose from based on desired performance and VRAM requirements. Similar models include the wizard-vicuna-13B-GPTQ and WizardLM-7B-GPTQ models, which provide alternative architectures and training datasets.

Model inputs and outputs

The wizard-mega-13B-GPTQ model is a text-to-text transformer model, taking natural language prompts as input and generating coherent and contextual responses. The model was trained on a large corpus of web data, allowing it to engage in open-ended conversations and tackle a wide variety of tasks.


  • Natural language prompts or instructions
  • Conversational context, such as previous messages in a chat


  • Coherent and contextual natural language responses
  • Continuations of provided prompts
  • Answers to questions or instructions


The wizard-mega-13B-GPTQ model is capable of engaging in open-ended dialogue, answering questions, and generating human-like text on a wide range of topics. It has demonstrated strong performance on language understanding and generation tasks, and can adapt its responses to the specific context and needs of the user.

What can I use it for?

The wizard-mega-13B-GPTQ model can be used for a variety of applications, such as building conversational AI assistants, generating creative writing, summarizing text, and even providing explanations and information on complex topics. The quantized versions available from TheBloke allow for efficient deployment on both GPU and CPU hardware, making it accessible for a wide range of use cases.

Things to try

One interesting aspect of the wizard-mega-13B-GPTQ model is its ability to engage in multi-turn conversations and adapt its responses based on the context. Try providing the model with a series of related prompts or questions, and see how it builds upon the previous responses to maintain a coherent and natural dialogue. Additionally, experiment with different prompting techniques, such as providing instructions or persona information, to see how the model's outputs can be tailored to your specific 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


The WizardCoder-Python-13B-V1.0-GPTQ is a large language model (LLM) created by WizardLM and maintained by TheBloke. It is a Llama 13B model that has been fine-tuned on datasets like ShareGPT, WizardLM, and Wizard-Vicuna to improve its abilities in text generation and task completion. The model has been quantized using GPTQ techniques to reduce its size and memory footprint, making it more accessible for various use cases. Model inputs and outputs Inputs Prompt**: A text prompt that the model uses to generate a response. Outputs Generated text**: The model's response to the provided prompt, which can be of varying length depending on the use case. Capabilities The WizardCoder-Python-13B-V1.0-GPTQ model is capable of generating human-like text on a wide range of topics. It can be used for tasks such as language modeling, text generation, and task completion. The model has been fine-tuned on datasets that cover a diverse range of subject matter, allowing it to engage in coherent and contextual conversations. What can I use it for? The WizardCoder-Python-13B-V1.0-GPTQ model can be used for a variety of applications, such as: Content generation**: The model can be used to generate articles, stories, or any other type of text content. Chatbots and virtual assistants**: The model can be integrated into chatbots and virtual assistants to provide natural language responses to user queries. Code generation**: The model can be used to generate code snippets or even complete programs based on natural language instructions. Things to try One interesting aspect of the WizardCoder-Python-13B-V1.0-GPTQ model is its ability to engage in open-ended conversations and task completion. You can try providing the model with a wide range of prompts, from creative writing exercises to technical programming tasks, and observe how it responds. The model's fine-tuning on diverse datasets allows it to handle a variety of subject matter, so feel free to experiment and see what kind of results you can get.

Read more

Updated Invalid Date




Total Score


The WizardCoder-Python-34B-V1.0 is a powerful large language model created by WizardLM. It is a 34 billion parameter model fine-tuned on the Evol Instruct Code dataset. This model surpasses the performance of GPT4 (2023/03/15), ChatGPT-3.5, and Claude2 on the HumanEval Benchmarks, achieving a 73.2 pass@1 score. In comparison, the WizardCoder-Python-13B-V1.0-GPTQ model is a 13 billion parameter version of the WizardCoder model that also achieves strong performance, surpassing models like Claude-Plus, Bard, and InstructCodeT5+. Model inputs and outputs Inputs Text prompt**: The model takes in a text prompt as input, which can be a natural language instruction, a coding task, or any other type of text-based input. Outputs Text response**: The model generates a text response that appropriately completes the given input prompt. This can be natural language text, code, or a combination of both. Capabilities The WizardCoder-Python-34B-V1.0 model has impressive capabilities when it comes to understanding and generating code. It can tackle a wide range of coding tasks, from simple programming exercises to more complex algorithmic problems. The model also demonstrates strong performance on natural language processing tasks, making it a versatile tool for various applications. What can I use it for? The WizardCoder-Python-34B-V1.0 model can be used for a variety of applications, including: Coding assistance**: Helping developers write more efficient and robust code by providing suggestions, explanations, and solutions to coding problems. Automated code generation**: Generating boilerplate code, prototypes, or even complete applications based on natural language descriptions. AI-powered programming tools**: Integrating the model into IDEs, code editors, or other programming tools to enhance developer productivity and creativity. Educational purposes**: Using the model to teach coding concepts, provide feedback on student submissions, or develop interactive programming tutorials. Research and experimentation**: Exploring the model's capabilities, testing new use cases, and contributing to the advancement of large language models for code-related tasks. Things to try One interesting aspect of the WizardCoder-Python-34B-V1.0 model is its ability to handle complex programming logic and solve algorithmic problems. You could try giving the model a challenging coding challenge or a problem from a coding competition and see how it performs. Additionally, you could experiment with different prompting strategies to see how the model responds to more open-ended or creative tasks, such as generating novel algorithms or suggesting innovative software design patterns.

Read more

Updated Invalid Date




Total Score


The WizardCoder-15B-1.0-GPTQ is a 15 billion parameter language model created by TheBloke and is based on the original WizardLM WizardCoder-15B-V1.0 model. It has been quantized to 4-bit precision using the AutoGPTQ tool, allowing for significantly reduced memory usage and faster inference speeds compared to the original full-precision model. This model is optimized for code-related tasks and demonstrates impressive performance on benchmarks like HumanEval, surpassing other open-source and even some closed-source models. Similar models include the WizardCoder-15B-1.0-GGML and WizardCoder-Python-13B-V1.0-GPTQ, which provide different quantization options and tradeoffs for users' hardware and requirements. Model inputs and outputs Inputs Instruction**: A textual description of a task or problem to solve. Outputs Response**: The model's generated solution or answer to the provided instruction, in the form of text. Capabilities The WizardCoder-15B-1.0-GPTQ model demonstrates strong performance on a variety of code-related tasks, including algorithm implementation, code generation, and problem-solving. It is able to understand natural language instructions and produce working, syntactically-correct code in various programming languages. What can I use it for? This model can be particularly useful for developers and programmers who need assistance with coding tasks, such as prototyping new features, solving algorithmic challenges, or generating boilerplate code. It could also be integrated into developer tools and workflows to enhance productivity and ideation. Additionally, the model's capabilities could be leveraged in educational settings to help teach programming concepts, provide interactive coding exercises, or offer personalized coding assistance to students. Things to try One interesting aspect of the WizardCoder-15B-1.0-GPTQ model is its ability to handle open-ended prompts and generate creative solutions. Try providing the model with ambiguous or underspecified instructions and observe how it interprets and responds to the task. This can uncover interesting insights about the model's understanding of context and its ability to reason about programming problems. Another area to explore is the model's performance on domain-specific tasks or languages. While the model is primarily trained on general code-related data, it may excel at certain types of programming challenges or excel at generating code in particular languages based on the nature of the training data.

Read more

Updated Invalid Date




Total Score


The wizard-mega-13B-GGML is a large language model created by OpenAccess AI Collective and quantized by TheBloke into GGML format for efficient CPU and GPU inference. It is based on the original Wizard Mega 13B model, which was fine-tuned on the ShareGPT, WizardLM, and Wizard-Vicuna datasets. The GGML format models provided here offer a range of quantization options to trade off between performance and accuracy. Similar models include WizardLM's WizardLM 7B GGML, Wizard Mega 13B - GPTQ, and June Lee's Wizard Vicuna 13B GGML. These models all leverage the original Wizard Mega 13B as a starting point and provide various quantization methods and formats for different hardware and inference needs. Model inputs and outputs The wizard-mega-13B-GGML model is a text-to-text transformer, meaning it takes natural language text as input and generates natural language text as output. The input can be any kind of text, such as instructions, questions, or prompts. The output is the model's response, which can range from short, direct answers to more open-ended, multi-sentence generations. Inputs Natural language text prompts, instructions, or questions Outputs Generated natural language text responses Capabilities The wizard-mega-13B-GGML model demonstrates strong text generation capabilities, able to engage in open-ended conversations, answer questions, and complete a variety of language tasks. It can be used for applications like chatbots, question-answering systems, content generation, and more. What can I use it for? The wizard-mega-13B-GGML model can be a powerful tool for a variety of language-based applications. For example, you could use it to build a chatbot that can engage in natural conversations, a question-answering system to help users find information, or a content generation system to produce draft articles, stories, or other text-based content. The flexibility of the model's text-to-text capabilities means it can be adapted to many different use cases. Companies could potentially monetize the wizard-mega-13B-GGML model by incorporating it into products and services that leverage its language understanding and generation abilities, such as customer service chatbots, writing assistants, or specialized content creation tools. Things to try One interesting thing to try with the wizard-mega-13B-GGML model is to experiment with different prompting strategies. By crafting prompts that provide context, instructions, or constraints, you can guide the model to generate responses that align with your specific needs. For example, you could try prompting the model to write a story about a particular topic, or to answer a question in a formal, professional tone. Another idea is to fine-tune the model on your own specialized dataset, which could allow it to perform even better on domain-specific tasks. The GGML format makes the model easy to integrate into various inference frameworks and applications.

Read more

Updated Invalid Date