Instructions to use theprint/ComputerScience-v1-2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theprint/ComputerScience-v1-2B-GGUF with Transformers:

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("theprint/ComputerScience-v1-2B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use theprint/ComputerScience-v1-2B-GGUF 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 theprint/ComputerScience-v1-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf theprint/ComputerScience-v1-2B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf theprint/ComputerScience-v1-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf theprint/ComputerScience-v1-2B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf theprint/ComputerScience-v1-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf theprint/ComputerScience-v1-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/theprint/ComputerScience-v1-2B-GGUF:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use theprint/ComputerScience-v1-2B-GGUF with Ollama:
```
ollama run hf.co/theprint/ComputerScience-v1-2B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use theprint/ComputerScience-v1-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theprint/ComputerScience-v1-2B-GGUF: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": "theprint/ComputerScience-v1-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use theprint/ComputerScience-v1-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/theprint/ComputerScience-v1-2B-GGUF:Q4_K_M
```

Lemonade

How to use theprint/ComputerScience-v1-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull theprint/ComputerScience-v1-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ComputerScience-v1-2B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use theprint/ComputerScience-v1-2B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theprint/ComputerScience-v1-2B-GGUF: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 theprint/ComputerScience-v1-2B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use theprint/ComputerScience-v1-2B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theprint/ComputerScience-v1-2B-GGUF: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 "theprint/ComputerScience-v1-2B-GGUF: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"

ComputerScience-v1-2B-GGUF

File size: 2,677 Bytes

c8de057

---
base_model: unsloth/Qwen3.5-2B
tags:
- fine-tuned
- lora
- sft
- auto-sft
language:
- en
library_name: transformers
---

# ComputerScience-v1-2B (GGUF)

A fine-tuned version of [`unsloth/Qwen3.5-2B`](https://huggingface.co/unsloth/Qwen3.5-2B) trained on **ComputerScience ML AI Chatml 7.0k 110926 train** data using [Auto-SFT](https://github.com/theprint/auto-sft) — an automated hyperparameter search and supervised fine-tuning pipeline.

The base model was adapted to follow the style and content of the `ComputerScience ML AI Chatml 7.0k 110926 train` dataset. Expect improved performance on tasks similar to those represented in the training data.

## Model Details

| Property | Value |
|---|---|
| Base model | `unsloth/Qwen3.5-2B` |
| Training data | `data/ComputerScience-ML-AI-Chatml-7.0k-110926_train.json` |
| Fine-tuning epochs | 2 |
| Fine-tuning date | 2026-09-12 |
| Fine-tuning method | LoRA (merged to full 16-bit) |

## Training Hyperparameters

### LoRA

| Parameter | Value |
|---|---|
| `r` | `4` |
| `alpha` | `8` |
| `dropout` | `0.02` |
| `target_modules` | `['q_proj', 'v_proj', 'k_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj']` |

### Training

| Parameter | Value |
|---|---|
| `learning_rate` | `0.0005` |
| `batch_size` | `4` |
| `gradient_accumulation_steps` | `1` |
| `warmup_ratio` | `0.0` |
| `max_seq_length` | `2048` |
| `quantization` | `none` |

## GGUF Files

These quantized GGUF files can be used directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://ollama.com/), [LM Studio](https://lmstudio.ai/), and other compatible runtimes.

| File | Description |
|---|---|
| `ComputerScience-v1-2B-GGUF-BF16.gguf` | BF16 |
| `ComputerScience-v1-2B-GGUF-Q8_0.gguf` | 8-bit — near-lossless, larger file |
| `ComputerScience-v1-2B-GGUF-Q6_K.gguf` | 6-bit — high quality |
| `ComputerScience-v1-2B-GGUF-Q5_K_M.gguf` | 5-bit medium — good quality/size balance |
| `ComputerScience-v1-2B-GGUF-Q5_K_S.gguf` | Q5_K_S |
| `ComputerScience-v1-2B-GGUF-Q4_K_M.gguf` | 4-bit medium — recommended for most use cases |
| `ComputerScience-v1-2B-GGUF-Q4_K_S.gguf` | Q4_K_S |
| `ComputerScience-v1-2B-GGUF-Q3_K_L.gguf` | Q3_K_L |
| `ComputerScience-v1-2B-GGUF-Q3_K_M.gguf` | Q3_K_M |
| `ComputerScience-v1-2B-GGUF-Q3_K_S.gguf` | Q3_K_S |
| `ComputerScience-v1-2B-GGUF-Q2_K.gguf` | 2-bit — smallest size, lowest quality |
| `ComputerScience-v1-2B-GGUF-IQ4_XS.gguf` | IQ4_XS |
| `ComputerScience-v1-2B-GGUF-IQ4_NL.gguf` | IQ4_NL |
| `ComputerScience-v1-2B-GGUF-TQ2_0.gguf` | TQ2_0 |

---
*Generated by [Auto-SFT](https://github.com/theprint/auto-sft) — automated LoRA fine-tuning with hyperparameter search.*