Image-Text-to-Text
MLX
Safetensors
llada2_moe
dllm
diffusion
llm
text_generation
conversational
custom_code
Instructions to use mlx-community/LLaDA2.1-mini-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/LLaDA2.1-mini-bf16 with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("mlx-community/LLaDA2.1-mini-bf16") config = load_config("mlx-community/LLaDA2.1-mini-bf16") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- Pi new
How to use mlx-community/LLaDA2.1-mini-bf16 with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/LLaDA2.1-mini-bf16"
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": "mlx-community/LLaDA2.1-mini-bf16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use mlx-community/LLaDA2.1-mini-bf16 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 "mlx-community/LLaDA2.1-mini-bf16"
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 mlx-community/LLaDA2.1-mini-bf16
Run Hermes
hermes
| { | |
| "architectures": [ | |
| "LLaDA2MoeModelLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_llada2_moe.LLaDA2MoeConfig", | |
| "AutoModel": "modeling_llada2_moe.LLaDA2MoeModel", | |
| "AutoModelForCausalLM": "modeling_llada2_moe.LLaDA2MoeModelLM" | |
| }, | |
| "dtype": "bfloat16", | |
| "embedding_dropout": 0.0, | |
| "first_k_dense_replace": 1, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5120, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "llada2_moe", | |
| "moe_intermediate_size": 512, | |
| "moe_router_enable_expert_bias": true, | |
| "n_group": 8, | |
| "norm_head": false, | |
| "norm_softmax": false, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 16, | |
| "num_experts": 256, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 20, | |
| "num_key_value_heads": 4, | |
| "num_shared_experts": 1, | |
| "output_dropout": 0.0, | |
| "output_router_logits": false, | |
| "pad_token_id": 156892, | |
| "partial_rotary_factor": 0.5, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 600000, | |
| "rotary_dim": 64, | |
| "routed_scaling_factor": 2.5, | |
| "router_dtype": "fp32", | |
| "score_function": "sigmoid", | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "topk_group": 4, | |
| "transformers_version": "4.57.1", | |
| "use_bias": false, | |
| "use_cache": false, | |
| "use_qkv_bias": false, | |
| "use_rmsnorm": true, | |
| "use_sliding_window": false, | |
| "using_split_qkv_in_self_attention": false, | |
| "vocab_size": 157184 | |
| } |