Instructions to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning 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 ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning
# Run inference directly in the terminal:
llama cli -hf ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning
# Run inference directly in the terminal:
llama cli -hf ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning

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 ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning
# Run inference directly in the terminal:
./llama-cli -hf ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning

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 ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning

Use Docker

docker model run hf.co/ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning

LM Studio
Jan

vLLM

How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning

Ollama
How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with Ollama:
```
ollama run hf.co/ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning
```

Unsloth Studio

How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning to start chatting

How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning"

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 "ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

MLX LM

How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with Docker Model Runner:
```
docker model run hf.co/ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning
```

Lemonade

How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning

Run and chat with the model

lemonade run user.Qwen-2.5-3B-Reasoning-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning"

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 ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning

Run Hermes

hermes

Atomic Chat

Model Overview

This model is a fine-tuned version of the Qwen2.5-3B base model, enhanced using Low-Rank Adaptation (LoRA) techniques via the MLX framework. The fine-tuning process utilized the isaiahbjork/chain-of-thought dataset, comprising 7,143 examples, over 600 iterations. This enhancement aims to improve the model's performance in tasks requiring multi-step reasoning and problem-solving.

Model Architecture

Base Model: Qwen2.5-3B
Model Type: Causal Language Model
Architecture: Transformer with Rotary Position Embedding (RoPE), SwiGLU activation, RMSNorm normalization, attention QKV bias, and tied word embeddings
Parameters: 3.09 billion
Layers: 36
Attention Heads: 16 for query, 2 for key and value (GQA)

Fine-Tuning Details

Technique: Low-Rank Adaptation (LoRA)
Framework: MLX
Dataset: isaiahbjork/chain-of-thought
Dataset Size: 7,143 examples
Iterations: 600

LoRA was employed to efficiently fine-tune the model by adjusting a subset of parameters, reducing computational requirements while maintaining performance. The MLX framework facilitated this process, leveraging Apple silicon hardware for optimized training.

Downloads last month: 19

MLX

Hardware compatibility

Quantized

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

(266)

this model

ApatheticWithoutTheA
/

Qwen-2.5-3B-Reasoning

Model Overview

Model Architecture

Fine-Tuning Details

Model tree for ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning

Dataset used to train ApatheticWithoutTheA/Qwen-2.5-3B-Reasoning