Instructions to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling with Transformers:

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

pipe = pipeline("text-generation", model="shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling 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 shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling: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 shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling: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 shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M

Use Docker

docker model run hf.co/shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M

LM Studio
Jan

vLLM

How to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M

SGLang

How to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling 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 "shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling" \
    --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": "shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling",
		"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 "shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling" \
        --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": "shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling with Ollama:
```
ollama run hf.co/shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M
```
Unsloth Desktop

How to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling: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": "shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling with Docker Model Runner:
```
docker model run hf.co/shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M
```

Lemonade

How to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M

Run and chat with the model

lemonade run user.NDP-Nemotron-3-Nano-4B-tool-calling-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling: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 shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling: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 "shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling: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"

NDP Nemotron-3 Nano 4B — Tool Calling

Fine-tune of unsloth/NVIDIA-Nemotron-3-Nano-4B on synthetic tool-use traces for the National Data Platform (NDP) MCP server. The model emits <tool_call> blocks invoking three NDP catalog tools: list_organizations, search_datasets, and get_dataset_details.

Quick stats


Base model	unsloth/NVIDIA-Nemotron-3-Nano-4B (hybrid Mamba+Attention, 4B params)
Training method	LoRA (r=8, alpha=16) via Unsloth + TRL SFTTrainer
Training data	1299 synthetic NDP tool-use examples, generated with gpt-oss:120b as teacher and curated with LLM-as-judge (threshold 7.0)
Steps / epochs	980 steps (~3 epochs)
Final train loss	0.0266
Training time	2725 s on 1× NVIDIA GH200
Peak VRAM	43.9 GB
Max seq length	4096

Intended use

This model is for tool-call generation against the NDP MCP server. Given a natural-language NDP query plus the three-tool catalog as tools=... to apply_chat_template, the model produces a tool call in Nemotron's XML format:

<tool_call>
<function=search_datasets>
<parameter=search_terms>
["climate"]
</parameter>
<parameter=server>
global
</parameter>
</function>
</tool_call>

NDP tool surface trained on

tool	purpose
`list_organizations(name_filter?, server?)`	List data publishers, optionally filtered
`search_datasets(...)`	Simple (search_terms[]) or advanced (owner_org, resource_format, filter_list, …) dataset search
`get_dataset_details(dataset_identifier, identifier_type?, server?)`	Full metadata by UUID or name slug

Tool catalog source-of-truth: configs/tools/ndp_tools.json.

Inference

The Nemotron-3 Nano family needs:

transformers>=5.3,<=5.5.0 (uses TokenizersBackend introduced in v5; capped by unsloth-zoo)
mamba_ssm==2.2.5 + causal_conv1d==1.5.2 (CUDA kernels compiled for your arch)
use_cache=False in generate() (current Nemotron-H modeling has a bug with cache_position)

import torch
# COMPAT: mamba_ssm 2.2.5 imports a class removed in transformers v5
import transformers.generation as _g, transformers.generation.utils as _gu
for cls in ("GreedySearchDecoderOnlyOutput", "SampleDecoderOnlyOutput"):
    if not hasattr(_g, cls):
        setattr(_g, cls, getattr(_gu, "GenerateDecoderOnlyOutput", _gu.ModelOutput))

from unsloth import FastLanguageModel
model, tok = FastLanguageModel.from_pretrained("shazzadulimun/NDP-Nemotron-3-Nano-4B-tool-calling", max_seq_length=4096, trust_remote_code=True)
FastLanguageModel.for_inference(model)

import json
TOOLS = json.load(open("ndp_tools_for_chat_template.json"))   # the catalog
messages = [{"role":"user","content":"Find datasets about climate."}]
text = tok.apply_chat_template(messages, tools=TOOLS, tokenize=False, add_generation_prompt=True)
inputs = tok(text, return_tensors="pt").to("cuda")
out = model.generate(
    **inputs, max_new_tokens=512, do_sample=False, use_cache=False,
    eos_token_id=tok.convert_tokens_to_ids("<|im_end|>"),
    stop_strings=["</function>"], tokenizer=tok,
)
print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))

Known limitations

Phantom None parameters: the model often emits ALL schema parameters with None values for the unused ones (e.g. a list_organizations call may include dataset_name=None, search_terms=None, etc.). This is a learned artifact of seeing the full schema in the system message during training. Use a post-parser to strip parameters whose value is None/null/empty before invoking the real MCP server. Reference parser: test_inference.py:parse_tool_call.
Looping on some queries: rarely (≈ 1/8 in our smoke test) the model loops on <parameter> blocks without emitting </function>. The tolerant parser variant recovers args even from truncated output. Setting stop_strings=["</function>"] at generation time helps when the model does emit it.
NDP-specific only: the model has seen exactly three tools. It is not a general tool-use model — it will not generalize to other MCP catalogs.

Training data generation pipeline

NDP MCP server (3 tools)
   │
   ├─ tool-generate-full           (gpt-oss:120b)   → 1879 raw examples
   ├─ schema-filter                                 → 1879 (no drops)
   ├─ tool-curate                  (gpt-oss:120b)   → 1712 kept @ threshold 7.0
   └─ prepare_data.py → fine-tune  (Unsloth + TRL)

Generator + curator: SIslamMun/Generator.

Files in this repo

file	purpose
`model.safetensors`	fp16 merged weights (~7.5 GB) — load with `transformers`
`tokenizer.json` + `tokenizer_config.json` + `chat_template.jinja`	tokenizer + Nemotron tool-aware chat template
`modeling_nemotron_h.py` + `configuration_nemotron_h.py`	dynamic remote code (required by `trust_remote_code=True`)
`*.gguf` (if uploaded)	GGUF quantizations for llama.cpp / Ollama / LMStudio