Hito is a 1.7B parameter model with structured thinking patterns that enable better accuracy and transparency.
For the original model (safetensors), training details, benchmarks, and full documentation, see the
main repository.
1# Download the recommended quantization
2wget https://huggingface.co/hitonet/hito-1.7b-GGUF/resolve/main/hito-1.7b-Q4_K_M.gguf
3
4# Create Modelfile
5cat > Modelfile << 'EOF'
6FROM hito-1.7b-Q4_K_M.gguf
7SYSTEM "You are Hito by Hitonet.com."
8PARAMETER temperature 0.7
9PARAMETER stop "<|im_end|>"
10EOF
11
12# Create and run
13ollama create hito -f Modelfile
14ollama run hito
1./llama-cli -m hito-1.7b-Q4_K_M.gguf \
2 -sys "You are Hito by Hitonet.com." \
3 -p "What is your name?" \
4 -n 256
For full documentation, benchmarks, and training details, see the
main repository.
The model weights are open source under Apache 2.0. You may use, modify, and distribute them freely.
The training methodology and cognitive framework used to create this model are proprietary to Hitonet.
For commercial licensing inquiries:
legal@hitonet.com
-green?style=flat-square){kind=icon}
