Instructions to use EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use EryriLabs/Llama-3.2-SARAThinker-merged-3b-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 EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16

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 EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16

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 EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16

Use Docker

docker model run hf.co/EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16

LM Studio
Jan
Ollama
How to use EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF with Ollama:
```
ollama run hf.co/EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16
```
Unsloth Desktop
Docker Model Runner
How to use EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF with Docker Model Runner:
```
docker model run hf.co/EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16
```

Lemonade

How to use EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EryriLabs/Llama-3.2-SARAThinker-merged-3b-GGUF:F16

Run and chat with the model

lemonade run user.Llama-3.2-SARAThinker-merged-3b-GGUF-F16

List all available models

lemonade list

Atomic Chat

Llama-3.2-SARAThinker-merged-3b

This is a merge of pre-trained language models created using mergekit. It was developed as part of an ongoing blog series. I take no responsibility for the ouputs of this model.

Merge Details

Merge Method

This model was merged using the TIES merge method using EryriLabs/Llama-3.2-SARA-3b as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: EryriLabs/Llama-3.2-SARA-3b
    parameters:
      density: 0.99  # keeping 90% of base model weights
  - model: Lyte/Llama-3.2-3B-Overthinker
    parameters:
      density: 0.1  # fraction of weights in differences from the base model to retain
      weight:   # weight gradient
        - filter: mlp
          value: 0.1
        - value: 0
  - model: HollowMan6/Llama-3.2-3B-SFT-Model-Ocra-500k
    parameters:
      density: 0.1
      weight: 0.2
merge_method: ties
base_model: EryriLabs/Llama-3.2-SARA-3b
parameters:
  normalize: true
  int8_mask: true
dtype: float16