vorenthos-architect-31b — Ollama Export
Exported from a local Ollama installation and uploaded to the Hugging Face Hub by vorenthiclabs.
Model Details
| Field | Value |
|---|---|
| Base model | claude |
| Finetuned model | vorenthos-architect-31b |
| Tag / variant | latest |
| Model type | Text Generation |
| Format | GGUF (llama.cpp-compatible) |
| Total size | 11.26 GB |
| Layers | 3 |
Quick Start
With Ollama (recommended)
ollama pull vorenthos-architect-31b
ollama run vorenthos-architect-31b
With llama.cpp / llama-cpp-python (GGUF)
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="vorenthiclabs/vorenthos-architect-31b",
filename="*.gguf",
)
output = llm("Hello, who are you?", max_tokens=256)
print(output["choices"][0]["text"])
With Hugging Face transformers + GGUF support
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("vorenthiclabs/vorenthos-architect-31b")
model = AutoModelForCausalLM.from_pretrained("vorenthiclabs/vorenthos-architect-31b")
File Structure
| File | Description |
|---|---|
config.json | Ollama model configuration / metadata |
model-*.gguf | Quantised weights in GGUF format |
tokenizer.jinja | Chat template |
params.json | Generation parameters (temperature, top-p, …) |
system_prompt.txt | Default system prompt embedded in the model |
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.