Instructions to use mervinpraison/llama3.2-3B-instruct-ur-fall with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mervinpraison/llama3.2-3B-instruct-ur-fall with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mervinpraison/llama3.2-3B-instruct-ur-fall", dtype="auto")

llama-cpp-python

How to use mervinpraison/llama3.2-3B-instruct-ur-fall with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mervinpraison/llama3.2-3B-instruct-ur-fall",
	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 mervinpraison/llama3.2-3B-instruct-ur-fall with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mervinpraison/llama3.2-3B-instruct-ur-fall: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 mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mervinpraison/llama3.2-3B-instruct-ur-fall: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 mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M

Use Docker

docker model run hf.co/mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M

LM Studio
Jan
Ollama
How to use mervinpraison/llama3.2-3B-instruct-ur-fall with Ollama:
```
ollama run hf.co/mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M
```

Unsloth Studio new

How to use mervinpraison/llama3.2-3B-instruct-ur-fall 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 mervinpraison/llama3.2-3B-instruct-ur-fall 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 mervinpraison/llama3.2-3B-instruct-ur-fall to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mervinpraison/llama3.2-3B-instruct-ur-fall to start chatting

Pi new

How to use mervinpraison/llama3.2-3B-instruct-ur-fall with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mervinpraison/llama3.2-3B-instruct-ur-fall with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mervinpraison/llama3.2-3B-instruct-ur-fall: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 mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use mervinpraison/llama3.2-3B-instruct-ur-fall with Docker Model Runner:
```
docker model run hf.co/mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M
```

Lemonade

How to use mervinpraison/llama3.2-3B-instruct-ur-fall with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mervinpraison/llama3.2-3B-instruct-ur-fall:Q4_K_M

Run and chat with the model

lemonade run user.llama3.2-3B-instruct-ur-fall-Q4_K_M

List all available models

lemonade list

Uploaded model

Developed by: mervinpraison
License: apache-2.0
Finetuned from model : unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit

UR Fall Detection Dataset

Dataset renamed to: mervinpraison/ur-fall-raw

(test) ➜  test praisonai train \
    --model unsloth/Llama-3.2-3B-Instruct-bnb-4bit \
    --dataset mervinpraison/test-dataset-2 \
    --hf mervinpraison/llama3.2-3B-instruct-test-2 \
    --ollama mervinpraison/llama3.2-3B-instruct-test-2

Conda environment 'praison_env' found.
🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.
🦥 Unsloth Zoo will now patch everything to make training faster!
DEBUG: Loaded config: {'dataset': [{'name': 'mervinpraison/test-dataset-2'}], 'dataset_num_proc': 2, 'dataset_text_field':
'text', 'gradient_accumulation_steps': 2, 'hf_model_name': 'mervinpraison/llama3.2-3B-instruct-test-2', 
'huggingface_save': 'true', 'learning_rate': 0.0002, 'load_in_4bit': True, 'loftq_config': None, 'logging_steps': 1, 
'lora_alpha': 16, 'lora_bias': 'none', 'lora_dropout': 0, 'lora_r': 16, 'lora_target_modules': ['q_proj', 'k_proj', 
'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj'], 'lr_scheduler_type': 'linear', 'max_seq_length': 2048, 
'max_steps': 10, 'model_name': 'unsloth/Llama-3.2-3B-Instruct-bnb-4bit', 'model_parameters': '8b', 'num_train_epochs': 1, 
'ollama_model': 'mervinpraison/llama3.2-3B-instruct-test-2', 'ollama_save': 'true', 'optim': 'adamw_8bit', 'output_dir': 
'outputs', 'packing': False, 'per_device_train_batch_size': 2, 'quantization_method': ['q4_k_m'], 'random_state': 3407, 
'seed': 3407, 'train': 'true', 'use_gradient_checkpointing': 'unsloth', 'use_rslora': False, 'warmup_steps': 5, 
'weight_decay': 0.01}

Downloads last month: 7

Safetensors

Model size

3B params

Tensor type

BF16

Inference Providers NEW

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