Instructions to use skshmjn/llama-3.2-3B-Mongo-query-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use skshmjn/llama-3.2-3B-Mongo-query-generator with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="skshmjn/llama-3.2-3B-Mongo-query-generator")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("skshmjn/llama-3.2-3B-Mongo-query-generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use skshmjn/llama-3.2-3B-Mongo-query-generator 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 skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf skshmjn/llama-3.2-3B-Mongo-query-generator: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 skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf skshmjn/llama-3.2-3B-Mongo-query-generator: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 skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M

Use Docker

docker model run hf.co/skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M

LM Studio
Jan

vLLM

How to use skshmjn/llama-3.2-3B-Mongo-query-generator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "skshmjn/llama-3.2-3B-Mongo-query-generator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "skshmjn/llama-3.2-3B-Mongo-query-generator",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M

SGLang

How to use skshmjn/llama-3.2-3B-Mongo-query-generator with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "skshmjn/llama-3.2-3B-Mongo-query-generator" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "skshmjn/llama-3.2-3B-Mongo-query-generator",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "skshmjn/llama-3.2-3B-Mongo-query-generator" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "skshmjn/llama-3.2-3B-Mongo-query-generator",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use skshmjn/llama-3.2-3B-Mongo-query-generator with Ollama:
```
ollama run hf.co/skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M
```
Unsloth Desktop

How to use skshmjn/llama-3.2-3B-Mongo-query-generator with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf skshmjn/llama-3.2-3B-Mongo-query-generator: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": "skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use skshmjn/llama-3.2-3B-Mongo-query-generator with Docker Model Runner:
```
docker model run hf.co/skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M
```

Lemonade

How to use skshmjn/llama-3.2-3B-Mongo-query-generator with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M

Run and chat with the model

lemonade run user.llama-3.2-3B-Mongo-query-generator-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use skshmjn/llama-3.2-3B-Mongo-query-generator with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf skshmjn/llama-3.2-3B-Mongo-query-generator: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 skshmjn/llama-3.2-3B-Mongo-query-generator:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use skshmjn/llama-3.2-3B-Mongo-query-generator with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf skshmjn/llama-3.2-3B-Mongo-query-generator: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 "skshmjn/llama-3.2-3B-Mongo-query-generator: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"

Need to understand the way we've prepared the dataset

by SeethuAI - opened Sep 30, 2025

Discussion

SeethuAI

Sep 30, 2025

Hello Team,

I've pretty much liked the approach you've considered for finetuning the model. I have a similar kind of requirement, but i've swamped with multiple options out there, like unlsoth and many more. Could you please help me with the script you've used to make my life easy to finetune based on my own database data ? Also, unlike the scenario here, i have a simple one DB and multiple collections in it. Please help me with a way that i can actually start with preparing the dataset and eventually run a script to fine tune.

Thank You in advance.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment