Instructions to use smdesai/Nemotron-Labs-Diffusion-3B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smdesai/Nemotron-Labs-Diffusion-3B-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("smdesai/Nemotron-Labs-Diffusion-3B-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

Pi new

How to use smdesai/Nemotron-Labs-Diffusion-3B-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "smdesai/Nemotron-Labs-Diffusion-3B-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "smdesai/Nemotron-Labs-Diffusion-3B-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use smdesai/Nemotron-Labs-Diffusion-3B-4bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "smdesai/Nemotron-Labs-Diffusion-3B-4bit"

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 smdesai/Nemotron-Labs-Diffusion-3B-4bit

Run Hermes

hermes

MLX LM

How to use smdesai/Nemotron-Labs-Diffusion-3B-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "smdesai/Nemotron-Labs-Diffusion-3B-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "smdesai/Nemotron-Labs-Diffusion-3B-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "smdesai/Nemotron-Labs-Diffusion-3B-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Nemotron-Labs-Diffusion-3B-4bit / config.json

smdesai

Upload folder using huggingface_hub

eda61c4 verified 1 day ago

raw

history blame contribute delete

1.64 kB

	{
	"ar_loss_weight": 1.0,
	"architectures": [
	"NemotronLabsDiffusionModel"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_implementation": "sdpa",
	"auto_map": {
	"AutoConfig": "configuration_nemotron_labs_diffusion.NemotronLabsDiffusionConfig",
	"AutoModel": "modeling_nemotron_labs_diffusion.NemotronLabsDiffusionModel"
	},
	"block_size": 32,
	"bos_token_id": 1,
	"dlm_loss_weight": null,
	"dlm_paradigm": "bidirectional",
	"dp_varying_mask_ratio": false,
	"eos_token_id": 11,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"initializer_range": 0.02,
	"intermediate_size": 9216,
	"mask_token_id": 100,
	"max_position_embeddings": 262144,
	"mlp_bias": false,
	"model_type": "nemotron_labs_diffusion",
	"num_attention_heads": 32,
	"num_hidden_layers": 26,
	"num_key_value_heads": 8,
	"quantization": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"beta_fast": 32.0,
	"beta_slow": 1.0,
	"factor": 16.0,
	"llama_4_scaling_beta": 0.1,
	"mscale": 1.0,
	"mscale_all_dim": 1.0,
	"original_max_position_embeddings": 16384,
	"rope_theta": 1000000.0,
	"rope_type": "yarn"
	},
	"sliding_window": null,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "5.0.0",
	"use_cache": false,
	"vocab_size": 131072
	}