Anubis-Mini-11B-v1-Vision-OLLAMA

<img src="https://huggingface.co/EnlistedGhost/Anubis-Mini-11B-v1-Vision/resolve/main/img/mzgVxODzFf43mruui3NU8.png" alt="Example image" width="398" height="338">

-------------------------------------------------- <br /> ------- Anubis-Mini-11B-v1-Vision ------- <br /> --------------------------------------------------

Anubis-Mini-8B-v1 + Vision Tower

• Llama-3.2-11B-Vision (Vision Tower Source)
• Anubis-Mini-8B-v1 (Language Model Source)

!!!!!!!!!!!!$$$$$$$$$$$$$$$$$$$$$$$$$!!!!!!!!!!!!!!!!<br />###########################################<br />NOTICE: ---- Ollama v0.30.X ---- (And Newer)<br />###########################################

As of Ollama v0.30.X and newer, "mllama" type models (Llama3.2-Vision and others) are no longer compatible at this time!

What happened? Ollama completely replaced their backend for GGUF model runs

• To elaborate: they have done away with thier GO-Runners for GGUF files completely. Instead they now favor direct Llama.cpp client/server that they wrap to run GGUF models.

• Because of this, any Llama3.2-Vision based models are no longer supported with the above mentioned versions or higher. I however, do have an pull request that I will be submitting this week that adds support for "mllama" model typs (Multimodal-Llama)

Thank you for understanding, and I look forward to everyone being able to use this model that @TheDrummer made the original txt-only <br /> Version of because it's awesome!

---

This release contains: <br /> Ollama compatible GGUF converted and Quantized model files (Compatible with ONLY Ollama)

Compatibility:

• Compatible with Ollama v0.11.x --> v0.20.2+

Quantized GGUF version of:

• Anubis-Mini-11B-v1-Vision <br /> (by EnlistedGhost)

Original Model Link:

• EnlistedGhost/Anubis-Mini-11B-v1-Vision

---

-------------------------------------------------------------<br /> - GGUF Conversion and Quantization Details: -<br />-------------------------------------------------------------

Software used to convert Safetensors to GGUF:

• <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp (Version: b8189)</a>

Software used to create Quantized GGUF Files:

• <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a>

Specific GitHub Commit Point:

• <a href="https://github.com/ggml-org/llama.cpp/releases">b8189</a>

Converted to GGUF and Quantized by:

• EnlistedGhost

---

--------------------------<br /> ---- Original Info ---- <br /> --------------------------

(Crossposted from the link in the above section: "Model Details"): <br /> <br /> <br /> <br />

----------------------------------- <br /> Anubis-Mini-11B-v1-Vision <br /> -----------------------------------

Anubis-Mini-8B-v1 + Vision Tower

• Llama-3.2-11B-Vision (Vision Tower Source)
• Anubis-Mini-8B-v1 (Language Model Source)

---

Model Details

• Developed by: Meta, TheDrummer, EnlistedGhost
• Shared by: EnlistedGhost
• Model type: Llama-3.2-11B-Vision (Vision Tower Only) + Anubis-Mini-8B-v1
• Language(s) (NLP): English, Italian, German, Hindi, Thai, Spanish, French, Portuguese
• License: Llama3.3

Model Sources

• Repository #1: Anubis-Mini-8B-v1
• Repository #2: Llama-3.2-11B-Vision

---

Uses and/or Direct Use

• Same as Meta-Llama-3.3

Out-of-Scope Use

• Same as Meta-Llama-3.3

Bias, Risks, and Limitations

• Same as Meta-Llama-3.3

How to Get Started with the Model

• Same as Meta-Llama-3.3

Evaluation

• This model has NOT been evaluated! USE AT YOUR OWN RISK!

Testing Data

• This model has NOT been tested! USE AT YOUR OWN RISK!

---

Credit & Special Thanks

• Meta-Llama (Vision Tower Source)
• TheDrummer (Language Model Source)
• Huggingface (Tools that made this possible)

---

Technical Specifications

Software

• Huggingface-Safetensors
• Huggingface-CLI
• PyTorch
• Python-3.13
• Transformers