Instructions to use raviadi123/llama_3.2-3b-reasoner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use raviadi123/llama_3.2-3b-reasoner with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("raviadi123/llama_3.2-3b-reasoner", dtype="auto")

llama-cpp-python

How to use raviadi123/llama_3.2-3b-reasoner with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="raviadi123/llama_3.2-3b-reasoner",
	filename="unsloth.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use raviadi123/llama_3.2-3b-reasoner with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf raviadi123/llama_3.2-3b-reasoner:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf raviadi123/llama_3.2-3b-reasoner:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf raviadi123/llama_3.2-3b-reasoner:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf raviadi123/llama_3.2-3b-reasoner: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 raviadi123/llama_3.2-3b-reasoner:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf raviadi123/llama_3.2-3b-reasoner: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 raviadi123/llama_3.2-3b-reasoner:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf raviadi123/llama_3.2-3b-reasoner:Q4_K_M

Use Docker

docker model run hf.co/raviadi123/llama_3.2-3b-reasoner:Q4_K_M

LM Studio
Jan
Ollama
How to use raviadi123/llama_3.2-3b-reasoner with Ollama:
```
ollama run hf.co/raviadi123/llama_3.2-3b-reasoner:Q4_K_M
```

Unsloth Studio

How to use raviadi123/llama_3.2-3b-reasoner 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 raviadi123/llama_3.2-3b-reasoner 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 raviadi123/llama_3.2-3b-reasoner to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for raviadi123/llama_3.2-3b-reasoner to start chatting

Docker Model Runner
How to use raviadi123/llama_3.2-3b-reasoner with Docker Model Runner:
```
docker model run hf.co/raviadi123/llama_3.2-3b-reasoner:Q4_K_M
```

Lemonade

How to use raviadi123/llama_3.2-3b-reasoner with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull raviadi123/llama_3.2-3b-reasoner:Q4_K_M

Run and chat with the model

lemonade run user.llama_3.2-3b-reasoner-Q4_K_M

List all available models

lemonade list

Llama-3.2-3B Fine-tuned for Reasoning

Developed by: raviadi123
License: apache-2.0
Finetuned from model : Llama-3.2-3B

This model is a fine-tuned version of unsloth/Llama-3.2-3B, specifically trained on the OpenMathReasoning dataset to improve mathematical and logical reasoning.

This model was trained 2x faster with Unsloth and Hugging Face's TRL library.

Model Description

The model is designed to follow a "chain-of-thought" or "scratchpad" reasoning process. It first works through a problem, showing its steps, and then provides a final, clean solution. This is achieved by using a specific set of special tokens in the prompt and output.

How to Use

To properly trigger the model's reasoning capabilities, you must follow the prompt structure it was trained on.

Prompt Structure

The entire input prompt sent to the model should follow this exact format. You provide the system instruction, the user's question, and then the special token to cue the model to start its reasoning process.

You are given a problem.
Think about the problem and provide your working out.
Place it between <start_working_out> and <end_working_out>.
Then, provide your solution between <SOLUTION></SOLUTION>

{your_question_here}
<start_working_out>

Downloads last month: 9

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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