EnlistedGhost/Pixtral-12B-Ollama-GGUF

Pixtral 12B (GGUF) (Ollama Patched)

This is an Ollama patched version of Pixtral-12B (GGUF) with working projector (mmproj) files. Included in the below information are instructions on how to setup/create an ollama model using these gguf files and the supplied "Modelfile-Pixtral-12B-XXXX.md"

Model Description

Currently this model card and repository is being updated to be configured in such a way that hopefully will not require users to manually create an Ollama model using the files found here. Please be patient as it is expected to be finalized within the next few days at the latest.

• Developed by: [mistralai] [ggml-org]
• Shared by: [EnlistedGhost]
• Model type: [Quantized/GGUF]
• License: [Apache-2.0]

How to Get Started with the Model

Use the code below to get started with the model. [More information will be published later...]

Model Sources

• Repository: [EnlistedGhost/Pixtral-12B-Ollama-GGUF]

Model Usage (any/all)

• This release of Pixtral-12B-GGUF has NOT been evaluated for any form of use.
• !!! USE AT YOUR OWN RISK - NO WARRANTY IS PROVIDED OF ANY KIND !!!

Out-of-Scope Use

[More information will be published later...]

Bias, Risks, and Limitations

[More information will be published later...]

Training Details

Training sets and data are from [mistralai] [ggml-org]

(This is an off-shoot/decendant of those models)

Evaluation

• This release of Pixtral-12B-GGUF has NOT been evaluated in any scope or method.
• !!! USE AT YOUR OWN RISK - NO WARRANTY IS PROVIDED OF ANY KIND !!!

Citation

[MistalAI Pixtral-12B Original Paper]

Model Card Authors and Contact

[EnlistedGhost]