Instructions to use atmzed/Darwin-4B-Genesis-mlx-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use atmzed/Darwin-4B-Genesis-mlx-fp16 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("atmzed/Darwin-4B-Genesis-mlx-fp16")

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 atmzed/Darwin-4B-Genesis-mlx-fp16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "atmzed/Darwin-4B-Genesis-mlx-fp16"

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": "atmzed/Darwin-4B-Genesis-mlx-fp16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use atmzed/Darwin-4B-Genesis-mlx-fp16 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "atmzed/Darwin-4B-Genesis-mlx-fp16"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "atmzed/Darwin-4B-Genesis-mlx-fp16"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "atmzed/Darwin-4B-Genesis-mlx-fp16",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use atmzed/Darwin-4B-Genesis-mlx-fp16 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 "atmzed/Darwin-4B-Genesis-mlx-fp16"

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 atmzed/Darwin-4B-Genesis-mlx-fp16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use atmzed/Darwin-4B-Genesis-mlx-fp16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "atmzed/Darwin-4B-Genesis-mlx-fp16"

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 "atmzed/Darwin-4B-Genesis-mlx-fp16" \
  --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"

Darwin-4B-Genesis-mlx-fp16 / config.json

atmzed

Upload folder using huggingface_hub

5be2954 verified 6 months ago

Raw History Blame Contribute Delete

3.6 kB

{
    "architectures": [
        "Gemma4ForConditionalGeneration"
    ],
    "audio_config": null,
    "audio_token_id": 258881,
    "boa_token_id": 256000,
    "boi_token_id": 255999,
    "dtype": "bfloat16",
    "eoa_token_id": 258883,
    "eoa_token_index": 258883,
    "eoi_token_id": 258882,
    "eos_token_id": [
        1,
        106,
        50
    ],
    "image_token_id": 258880,
    "initializer_range": 0.02,
    "model_type": "gemma4",
    "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": 2560,
        "hidden_size_per_layer_input": 256,
        "initializer_range": 0.02,
        "intermediate_size": 10240,
        "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",
            "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": 131072,
        "model_type": "gemma4_text",
        "moe_intermediate_size": null,
        "num_attention_heads": 8,
        "num_experts": null,
        "num_global_key_value_heads": null,
        "num_hidden_layers": 42,
        "num_key_value_heads": 2,
        "num_kv_shared_layers": 18,
        "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": false,
        "vocab_size": 262144,
        "vocab_size_per_layer_input": 262144
    },
    "tie_word_embeddings": true,
    "transformers_version": "5.6.0.dev0",
    "video_token_id": 258884,
    "vision_soft_tokens_per_image": 280
}

	{
	"architectures": [
	"Gemma4ForConditionalGeneration"
	],
	"audio_config": null,
	"audio_token_id": 258881,
	"boa_token_id": 256000,
	"boi_token_id": 255999,
	"dtype": "bfloat16",
	"eoa_token_id": 258883,
	"eoa_token_index": 258883,
	"eoi_token_id": 258882,
	"eos_token_id": [
	1,
	106,
	50
	],
	"image_token_id": 258880,
	"initializer_range": 0.02,
	"model_type": "gemma4",
	"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": 2560,
	"hidden_size_per_layer_input": 256,
	"initializer_range": 0.02,
	"intermediate_size": 10240,
	"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",
	"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": 131072,
	"model_type": "gemma4_text",
	"moe_intermediate_size": null,
	"num_attention_heads": 8,
	"num_experts": null,
	"num_global_key_value_heads": null,
	"num_hidden_layers": 42,
	"num_key_value_heads": 2,
	"num_kv_shared_layers": 18,
	"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": false,
	"vocab_size": 262144,
	"vocab_size_per_layer_input": 262144
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.6.0.dev0",
	"video_token_id": 258884,
	"vision_soft_tokens_per_image": 280
	}