Instructions to use bezau1/sezai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use bezau1/sezai with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bezau1/sezai:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bezau1/sezai:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bezau1/sezai:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bezau1/sezai:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf bezau1/sezai:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bezau1/sezai:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf bezau1/sezai:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bezau1/sezai:Q4_K_M

Use Docker

docker model run hf.co/bezau1/sezai:Q4_K_M

LM Studio
Jan
Ollama
How to use bezau1/sezai with Ollama:
```
ollama run hf.co/bezau1/sezai:Q4_K_M
```
Unsloth Desktop

How to use bezau1/sezai with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bezau1/sezai:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "bezau1/sezai:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use bezau1/sezai with Docker Model Runner:
```
docker model run hf.co/bezau1/sezai:Q4_K_M
```

Lemonade

How to use bezau1/sezai with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bezau1/sezai:Q4_K_M

Run and chat with the model

lemonade run user.sezai-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use bezau1/sezai with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bezau1/sezai:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default bezau1/sezai:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bezau1/sezai with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bezau1/sezai:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "bezau1/sezai:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Model Card for Model ID

This model is a personal finetune of Qwopus 3.5 trained by bezau1

Model Details

Model Description

This is a LoRA finetune of Qwopus 3.5, adapted using class material on Islam. The finetune is intended to make the base model more knowledgeable about and responsive to topics related to Islam (e.g. history, theology, practice), based on course/class content used as training data.

Developed by: bezau1
Shared by: bezau1
Model type: Causal language model (LoRA adapter / finetune)
License: apache-2.0
Finetuned from model: Qwopus 3.5

Uses

Direct Use

Intended for answering questions and generating text related to Islam, based on the class material used for training (e.g. for study, review, or exploring the source material conversationally).

Out-of-Scope Use

This model should not be treated as an authoritative religious, legal, or scholarly source. It reflects a specific set of class material and the biases/limitations of that material and of the base model, and should not be used for issuing religious rulings (fatwas), academic citation, or any context requiring verified theological accuracy.

Bias, Risks, and Limitations

Because this model was finetuned on a specific set of class material, its knowledge and perspective on Islam are limited to and shaped by that material — it may not reflect the full diversity of Islamic scholarship, schools of thought (madhab), or sectarian perspectives (e.g. Sunni, Shia, Sufi, etc.). It may also inherit any biases, errors, or gaps present in the source class material, as well as general limitations of the base Qwopus 3.5 model.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model. Outputs on religious topics should be verified against primary sources and qualified scholars rather than relied upon as authoritative. Not recommended for use in contexts requiring religious, legal, or academic authority.

Training Details

Training Data

Class material about Islam (specific source/dataset not further specified).

Training Procedure

LoRA (Low-Rank Adaptation) finetuning on top of Qwopus 3.5.

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: Not specified
Hours used: Not specified
Cloud Provider: Not specified
Compute Region: Not specified
Carbon Emitted: Not specified

Model Architecture and Objective

LoRA adapter finetuning Qwopus 3.5 for improved performance on Islam-related class material.

Hardware

Nvidia T4 Tensor

Software

LoRA (e.g. via peft/transformers, or equivalent tooling — not further specified)

Downloads last month: 12

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for bezau1/sezai

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 61