Instructions to use nikimoriOne/Pretype-One with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nikimoriOne/Pretype-One 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("nikimoriOne/Pretype-One")

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

How to use nikimoriOne/Pretype-One with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nikimoriOne/Pretype-One"

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": "nikimoriOne/Pretype-One"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use nikimoriOne/Pretype-One with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "nikimoriOne/Pretype-One"

Run an OpenAI-compatible server

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

Hermes Agent

How to use nikimoriOne/Pretype-One 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 "nikimoriOne/Pretype-One"

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 nikimoriOne/Pretype-One

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nikimoriOne/Pretype-One with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nikimoriOne/Pretype-One"

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 "nikimoriOne/Pretype-One" \
  --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"

Pretype-One / config.json

nikimori

Gemma 4 E2B Pretype, 4-bit MLX with a chat adapter

70cea30 verified about 20 hours ago

Raw History Blame Contribute Delete

2.97 kB

{
  "architectures": [
    "Gemma4ForConditionalGeneration"
  ],
  "audio_token_id": 81996,
  "boa_token_id": 81994,
  "boi_token_id": 81993,
  "dtype": "bfloat16",
  "eoa_token_id": 81998,
  "eoa_token_index": 81998,
  "eoi_token_id": 81997,
  "eos_token_id": 1,
  "image_token_id": 81995,
  "initializer_range": 0.02,
  "model_type": "gemma4",
  "quantization": {
    "group_size": 64,
    "bits": 4,
    "mode": "affine"
  },
  "quantization_config": {
    "group_size": 64,
    "bits": 4,
    "mode": "affine"
  },
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attention_k_eq_v": false,
    "bos_token_id": 2,
    "dtype": "bfloat16",
    "enable_moe_block": false,
    "eos_token_id": 1,
    "expert_intermediate_size": null,
    "final_logit_softcapping": 30.0,
    "global_head_dim": 512,
    "head_dim": 256,
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 1536,
    "hidden_size_per_layer_input": 256,
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "layer_types": [
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention"
    ],
    "max_position_embeddings": 131072,
    "model_type": "gemma4_text",
    "num_attention_heads": 8,
    "num_experts": null,
    "num_global_key_value_heads": null,
    "num_hidden_layers": 35,
    "num_key_value_heads": 1,
    "num_kv_shared_layers": 20,
    "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": 512,
    "tie_word_embeddings": true,
    "top_k_experts": null,
    "use_bidirectional_attention": null,
    "use_cache": true,
    "use_double_wide_mlp": true,
    "vocab_size": 82000,
    "vocab_size_per_layer_input": 82000
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.5.0.dev0",
  "video_token_id": 81999,
  "vision_soft_tokens_per_image": 280,
  "vocab_size": 82000
}

	{
	"architectures": [
	"Gemma4ForConditionalGeneration"
	],
	"audio_token_id": 81996,
	"boa_token_id": 81994,
	"boi_token_id": 81993,
	"dtype": "bfloat16",
	"eoa_token_id": 81998,
	"eoa_token_index": 81998,
	"eoi_token_id": 81997,
	"eos_token_id": 1,
	"image_token_id": 81995,
	"initializer_range": 0.02,
	"model_type": "gemma4",
	"quantization": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_k_eq_v": false,
	"bos_token_id": 2,
	"dtype": "bfloat16",
	"enable_moe_block": false,
	"eos_token_id": 1,
	"expert_intermediate_size": null,
	"final_logit_softcapping": 30.0,
	"global_head_dim": 512,
	"head_dim": 256,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 1536,
	"hidden_size_per_layer_input": 256,
	"initializer_range": 0.02,
	"intermediate_size": 6144,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 131072,
	"model_type": "gemma4_text",
	"num_attention_heads": 8,
	"num_experts": null,
	"num_global_key_value_heads": null,
	"num_hidden_layers": 35,
	"num_key_value_heads": 1,
	"num_kv_shared_layers": 20,
	"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": 512,
	"tie_word_embeddings": true,
	"top_k_experts": null,
	"use_bidirectional_attention": null,
	"use_cache": true,
	"use_double_wide_mlp": true,
	"vocab_size": 82000,
	"vocab_size_per_layer_input": 82000
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.5.0.dev0",
	"video_token_id": 81999,
	"vision_soft_tokens_per_image": 280,
	"vocab_size": 82000
	}