vorenthos-glare-2 — Ollama Export

🖼️ Vision-Language Model — accepts both image and text inputs.

Exported from a local Ollama installation and uploaded to the Hugging Face Hub by vorenthiclabs.

Model Details

Quick Start

With Ollama (recommended)

ollama pull vorenthos-glare-2
ollama run vorenthos-glare-2

With llama.cpp / llama-cpp-python (GGUF)

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="vorenthiclabs/vorenthos-glare-2",
    filename="*.gguf",
)
output = llm("Hello, who are you?", max_tokens=256)
print(output["choices"][0]["text"])

Vision input example (llama-cpp-python)

from llama_cpp import Llama
from llama_cpp.llama_chat_format import MoondreamChatHandler  # adjust handler per model

llm = Llama.from_pretrained(
    repo_id="vorenthiclabs/vorenthos-glare-2",
    filename="*.gguf",
    chat_handler=MoondreamChatHandler(clip_model_path="mmproj*.gguf"),
    n_ctx=4096,
)
response = llm.create_chat_completion(messages=[{
    "role": "user",
    "content": [
        {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}},
        {"type": "text",      "text": "Describe this image."}
    ]
}])
print(response["choices"][0]["message"]["content"])

With Hugging Face transformers + GGUF support

from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("vorenthiclabs/vorenthos-glare-2")
model     = AutoModelForCausalLM.from_pretrained("vorenthiclabs/vorenthos-glare-2")

File Structure

License

Please check the original model's license before redistribution.
This upload is provided as-is for research and experimentation.

About vorenthiclabs

Visit us at https://huggingface.co/vorenthiclabs.