Text Generation
MLX
Safetensors
inkling2_loop
code
craft
mirror
conversational
8-bit precision
modelopt
Instructions to use rao-studios/Inkling-2-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use rao-studios/Inkling-2-Mini 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("rao-studios/Inkling-2-Mini") 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 rao-studios/Inkling-2-Mini with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "rao-studios/Inkling-2-Mini"
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": "rao-studios/Inkling-2-Mini" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use rao-studios/Inkling-2-Mini with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "rao-studios/Inkling-2-Mini"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "rao-studios/Inkling-2-Mini" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8080/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rao-studios/Inkling-2-Mini", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use rao-studios/Inkling-2-Mini 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 "rao-studios/Inkling-2-Mini"
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 rao-studios/Inkling-2-Mini
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use rao-studios/Inkling-2-Mini with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "rao-studios/Inkling-2-Mini"
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 "rao-studios/Inkling-2-Mini" \ --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 rao-studios/Inkling-2-Mini: direct link, hf CLI and curl.
- Browser
- Download file 2.72 kB
-
https://huggingface.co/rao-studios/Inkling-2-Mini/resolve/main/config.json
- Command line
-
hf download hf://rao-studios/Inkling-2-Mini/config.json
-
curl -L -o config.json https://huggingface.co/rao-studios/Inkling-2-Mini/resolve/main/config.json
2.72 kB
| { | |
| "dtype": "bfloat16", | |
| "architectures": [ | |
| "Inkling2LoopForConditionalGeneration" | |
| ], | |
| "model_type": "inkling2_loop", | |
| "eos_token_id": 200006, | |
| "text_config": { | |
| "model_type": "inkling2_loop_text", | |
| "model_max_length": 1048576, | |
| "torch_dtype": "bfloat16", | |
| "hidden_size": 2304, | |
| "num_hidden_layers": 24, | |
| "vocab_size": 201024, | |
| "num_attention_heads": 24, | |
| "num_key_value_heads": 8, | |
| "head_dim": 128, | |
| "d_rel": 16, | |
| "rel_extent": 1024, | |
| "q_bias": false, | |
| "o_bias": false, | |
| "log_scaling_n_floor": 8192, | |
| "log_scaling_alpha": 0.1, | |
| "rms_norm_eps": 1e-06, | |
| "use_value_norm_no_gamma": true, | |
| "qk_l2_clip_threshold": 22.627416997969522, | |
| "rel_l2_clip_threshold": 8.0, | |
| "local_layer_ids": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 18, | |
| 19, | |
| 20, | |
| 21, | |
| 22 | |
| ], | |
| "sconv_kernel_size": 4, | |
| "unpadded_vocab_size": 200058, | |
| "final_logit_softcapping": 30.0, | |
| "swa_head_dim": 128, | |
| "swa_num_attention_heads": 24, | |
| "swa_num_key_value_heads": 8, | |
| "sliding_window_size": 1024, | |
| "n_layers_per_attn_res_block": 6, | |
| "attn_res_normalize_values": true, | |
| "n_routed_experts": 128, | |
| "num_experts_per_tok": 8, | |
| "n_shared_experts": 0, | |
| "intermediate_size": 1152, | |
| "mlp_gate_softcap": 4.0, | |
| "mlp_up_softcap": 25.0, | |
| "route_scale": 8.0, | |
| "use_gate_bias": true, | |
| "loop_config": { | |
| "core_start": 6, | |
| "core_end": 18, | |
| "num_passes": 3, | |
| "gate_rank": 64, | |
| "is_varloop": false | |
| } | |
| }, | |
| "vision_config": { | |
| "model_type": "inkling2_vision", | |
| "text_hidden_size": 2304, | |
| "temporal_patch_size": 2, | |
| "native_patch_size": 20, | |
| "adapter_merge_size": 2, | |
| "projection_hidden_dim": 4096, | |
| "projector_bias": false, | |
| "hidden_size": 1024, | |
| "num_hidden_layers": 23, | |
| "num_attention_heads": 16, | |
| "mlp_ratio": 4.0, | |
| "posemb_grid_size": 32, | |
| "layer_norm_eps": 1e-05 | |
| }, | |
| "mtp_config": { | |
| "hidden_size": 2304, | |
| "num_hidden_layers": 3, | |
| "num_attention_heads": 24, | |
| "num_key_value_heads": 8, | |
| "head_dim": 128, | |
| "intermediate_size": 9216, | |
| "max_position_embeddings": 1048576, | |
| "torch_dtype": "bfloat16", | |
| "q_bias": false, | |
| "o_bias": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "local_layer_ids": [ | |
| 0, | |
| 2 | |
| ], | |
| "sliding_window_size": 1024, | |
| "block_size": 8, | |
| "markov_rank": 256, | |
| "markov_head_type": "rnn_hidden", | |
| "target_layer_ids": [ | |
| 5, | |
| 23, | |
| 41, | |
| 48 | |
| ] | |
| }, | |
| "quantization_config": { | |
| "quant_method": "modelopt", | |
| "quant_algo": "NVFP4" | |
| } | |
| } | |