Text Generation
MLX
Safetensors
modilify_mk2
diffusion
mixture-of-experts
custom-code
modilify-mk2
conversational
Instructions to use modilify/Modilify-Mk2-preview-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use modilify/Modilify-Mk2-preview-mlx 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("modilify/Modilify-Mk2-preview-mlx") 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 Settings
- LM Studio
- Pi
How to use modilify/Modilify-Mk2-preview-mlx with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "modilify/Modilify-Mk2-preview-mlx"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "modilify/Modilify-Mk2-preview-mlx" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use modilify/Modilify-Mk2-preview-mlx with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "modilify/Modilify-Mk2-preview-mlx"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "modilify/Modilify-Mk2-preview-mlx" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "modilify/Modilify-Mk2-preview-mlx", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use modilify/Modilify-Mk2-preview-mlx 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 "modilify/Modilify-Mk2-preview-mlx"
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 modilify/Modilify-Mk2-preview-mlx
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use modilify/Modilify-Mk2-preview-mlx with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "modilify/Modilify-Mk2-preview-mlx"
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 "modilify/Modilify-Mk2-preview-mlx" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download config.json from modilify/Modilify-Mk2-preview-mlx: direct link, hf CLI and curl.
- Browser
- Download file 4.02 kB
-
https://huggingface.co/modilify/Modilify-Mk2-preview-mlx/resolve/main/config.json
- Command line
-
hf download hf://modilify/Modilify-Mk2-preview-mlx/config.json
-
curl -L -o config.json https://huggingface.co/modilify/Modilify-Mk2-preview-mlx/resolve/main/config.json
4.02 kB
| { | |
| "canvas_length": 256, | |
| "channel_end_token_id": 101, | |
| "commit_confidence_power": 1.0, | |
| "commit_entropy_weight": 1.0, | |
| "commit_failure_budget": 0.2, | |
| "commit_gold_alpha": 0.4, | |
| "commit_gold_weight": 0.2, | |
| "commit_min_p": 0.05, | |
| "commit_readiness_beta": 0.02, | |
| "commit_readiness_budget_margin": 0.02, | |
| "commit_readiness_failure_weight": 5.0, | |
| "commit_readiness_loss_weight": 0.5, | |
| "commit_readiness_objective": "frontier_prefix_budget_v2", | |
| "commit_readiness_target_tokens": 16, | |
| "commit_sequence_dim": 1024, | |
| "commit_sequence_layers": 2, | |
| "commit_target_confidence": 0.5, | |
| "commit_top_k": 40, | |
| "confidence_calibration_loss_weight": 0.01, | |
| "eos_token_id": 1, | |
| "initializer_range": 0.02, | |
| "kv_cache_bucket_size": 128, | |
| "latent_dim": 2816, | |
| "latent_ffn_dim": 7168, | |
| "latent_history_kv_rank": 1024, | |
| "latent_history_length": 16, | |
| "latent_history_views": 4, | |
| "latent_local_attention_window": 128, | |
| "latent_memory_slots": 256, | |
| "latent_num_heads": 16, | |
| "latent_num_layers": 4, | |
| "latent_persistent_bus_unfreeze_steps": 0, | |
| "latent_tape_probes": 4, | |
| "latent_tape_scheme": "gdn2_spatial_probe_v1", | |
| "latent_working_bus_unfreeze_steps": 0, | |
| "latent_working_last_block_global": true, | |
| "memory_architecture": "compact_gdn2_v2", | |
| "memory_scheme": "dual_timescale_gdn2_trajectory_memory", | |
| "model_type": "modilify_mk2", | |
| "persistent_memory_bus": true, | |
| "persistent_memory_write": "commit_only_transformer", | |
| "state_schema_version": 25, | |
| "terminal_stop_loss_weight": 0.01, | |
| "terminal_stop_target_probability": 0.9, | |
| "terminal_token_ids": [ | |
| 106, | |
| 50 | |
| ], | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 2, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 1, | |
| "final_logit_softcapping": 30.0, | |
| "global_head_dim": 512, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2816, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2112, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 262144, | |
| "model_type": "modilify_mk2_text", | |
| "moe_intermediate_size": 704, | |
| "num_attention_heads": 16, | |
| "num_experts": 128, | |
| "num_global_key_value_heads": 2, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 1000000.0, | |
| "rope_type": "proportional" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sliding_window": 1024, | |
| "tie_word_embeddings": true, | |
| "top_k_experts": 8, | |
| "use_bidirectional_attention": null, | |
| "vocab_size": 262144 | |
| }, | |
| "tie_word_embeddings": true, | |
| "token_ce_normalization": "per_sample_exposure_v1", | |
| "token_ce_supervision": "valid_canvas_v1", | |
| "token_loss_weight": 1.0, | |
| "training_bptt_steps": 16, | |
| "training_prefix_cache": "incremental", | |
| "training_scheme": "gold_prefix_shared_commit_0_256_committed_ce_calibration_causal_throughput_terminal_sft", | |
| "transformers_version": "5.14.1", | |
| "turn_end_token_id": 106, | |
| "vocab_chunk_size": 32768, | |
| "working_memory_bus": true, | |
| "writer_slot_gate": "per_slot" | |
| } | |