Image-Text-to-Text
MLX
Safetensors
minimax_m3_vl
multimodal
Mixture of Experts
agent
coding
video
conversational
custom_code
4-bit precision
Instructions to use mlx-community/MiniMax-M3-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/MiniMax-M3-4bit 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/MiniMax-M3-4bit") config = load_config("mlx-community/MiniMax-M3-4bit") # 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 Settings
- LM Studio
- Pi
How to use mlx-community/MiniMax-M3-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/MiniMax-M3-4bit"
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": "mlx-community/MiniMax-M3-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use mlx-community/MiniMax-M3-4bit 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 "mlx-community/MiniMax-M3-4bit"
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 mlx-community/MiniMax-M3-4bit
Run Hermes
hermes
| { | |
| "architectures": [ | |
| "MiniMaxM3SparseForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_minimax_m3_vl.MiniMaxM3VLConfig" | |
| }, | |
| "do_sample": true, | |
| "eos_token_id": 200020, | |
| "generation_config": { | |
| "bos_token_id": 200019, | |
| "do_sample": true, | |
| "eos_token_id": 200020, | |
| "temperature": 1.0, | |
| "top_p": 0.95, | |
| "transformers_version": "4.46.1" | |
| }, | |
| "image_grid_pinpoints": "[(336, 336), (336, 672), (336, 1008), (336, 1344), (336, 1680), (336, 2016), (672, 336), (672, 672), (672, 1008), (672, 1344), (672, 1680), (672, 2016), (1008, 336), (1008, 672), (1008, 1008), (1008, 1344), (1008, 1680), (1008, 2016), (1344, 336), (1344, 672), (1344, 1008), (1344, 1344), (1344, 1680), (1344, 2016), (1680, 336), (1680, 672), (1680, 1008), (1680, 1344), (1680, 1680), (1680, 2016), (2016, 336), (2016, 672), (2016, 1008), (2016, 1344), (2016, 1680), (2016, 2016)]", | |
| "image_seq_length": 576, | |
| "image_token_index": 200025, | |
| "img_token_compression_config": { | |
| "image_token_compression_method": "patch_merge", | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "model_type": "minimax_m3_vl", | |
| "multimodal_projector_bias": true, | |
| "num_reward_heads": 0, | |
| "process_image_mode": "dynamic_res", | |
| "projector_hidden_act": "gelu", | |
| "projector_hidden_size": 6144, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "language_model.model.layers.3.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "language_model.model.layers.3.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.25.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.26.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.27.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.28.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.29.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.30.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.31.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.32.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.33.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.34.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.36.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.37.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.38.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.39.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.40.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.41.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.42.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.43.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.44.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.45.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.46.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.47.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.48.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.49.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.50.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.51.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.52.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.53.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.54.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.55.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.56.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.57.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.58.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.59.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| } | |
| }, | |
| "temperature": 1.0, | |
| "text_config": { | |
| "hidden_size": 6144, | |
| "intermediate_size": 3072, | |
| "num_hidden_layers": 60, | |
| "num_attention_heads": 64, | |
| "num_key_value_heads": 4, | |
| "head_dim": 128, | |
| "vocab_size": 200064, | |
| "max_position_embeddings": 1048576, | |
| "rms_norm_eps": 1e-06, | |
| "use_gemma_norm": true, | |
| "attention_output_gate": false, | |
| "rope_theta": 5000000, | |
| "rotary_dim": 64, | |
| "partial_rotary_factor": 0.5, | |
| "hidden_act": "swigluoai", | |
| "use_qk_norm": true, | |
| "tie_word_embeddings": false, | |
| "dense_intermediate_size": 12288, | |
| "shared_intermediate_size": 3072, | |
| "num_local_experts": 128, | |
| "num_experts_per_tok": 4, | |
| "n_shared_experts": 1, | |
| "scoring_func": "sigmoid", | |
| "use_routing_bias": true, | |
| "moe_layer_freq": [ | |
| 0, | |
| 0, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1 | |
| ], | |
| "qk_norm_type": "per_head", | |
| "num_mtp_modules": 7, | |
| "num_nextn_predict_layers": 1, | |
| "swiglu_alpha": 1.702, | |
| "swiglu_limit": 7.0, | |
| "routed_scaling_factor": 2.0, | |
| "sparse_attention_config": { | |
| "use_sparse_attention": true, | |
| "sparse_index_dim": 128, | |
| "sparse_num_index_heads": 4, | |
| "sparse_topk_blocks": 16, | |
| "sparse_block_size": 128, | |
| "sparse_disable_index_value": [ | |
| 0, | |
| 0, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1 | |
| ], | |
| "sparse_score_type": "max", | |
| "sparse_init_block": 0, | |
| "sparse_local_block": 1, | |
| "sparse_attention_freq": [ | |
| 0, | |
| 0, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1 | |
| ] | |
| }, | |
| "architectures": [ | |
| "MiniMaxM3SparseForCausalLM" | |
| ] | |
| }, | |
| "top_p": 0.95, | |
| "transformers_version": "4.52.4", | |
| "video_token_index": 200026, | |
| "vision_config": { | |
| "hidden_size": 1280, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 32, | |
| "intermediate_size": 5120, | |
| "patch_size": 14, | |
| "image_size": 2016, | |
| "projection_dim": 6144, | |
| "position_embedding_type": "rope", | |
| "rope_mode": "3d", | |
| "rope_theta": 10000.0, | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-05, | |
| "model_type": "clip_vision_model", | |
| "num_channels": 3, | |
| "vocab_size": 32000, | |
| "img_token_compression_config": { | |
| "image_token_compression_method": "patch_merge", | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_segment_max_frames": 4 | |
| }, | |
| "vision_feature_layer": -1, | |
| "vision_feature_select_strategy": "full" | |
| } |