Instructions to use OsaurusAI/Osaurus-AppleScript-8B-JANG_6M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/Osaurus-AppleScript-8B-JANG_6M 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("OsaurusAI/Osaurus-AppleScript-8B-JANG_6M")

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 OsaurusAI/Osaurus-AppleScript-8B-JANG_6M with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/Osaurus-AppleScript-8B-JANG_6M"

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": "OsaurusAI/Osaurus-AppleScript-8B-JANG_6M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OsaurusAI/Osaurus-AppleScript-8B-JANG_6M 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 "OsaurusAI/Osaurus-AppleScript-8B-JANG_6M"

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 OsaurusAI/Osaurus-AppleScript-8B-JANG_6M

Run Hermes

hermes

OpenClaw new

How to use OsaurusAI/Osaurus-AppleScript-8B-JANG_6M with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/Osaurus-AppleScript-8B-JANG_6M"

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 "OsaurusAI/Osaurus-AppleScript-8B-JANG_6M" \
  --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"

MLX LM

How to use OsaurusAI/Osaurus-AppleScript-8B-JANG_6M with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "OsaurusAI/Osaurus-AppleScript-8B-JANG_6M"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OsaurusAI/Osaurus-AppleScript-8B-JANG_6M"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OsaurusAI/Osaurus-AppleScript-8B-JANG_6M",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Osaurus-AppleScript-8B-JANG_6M / config.json

Osaurus-AI

Fixed JANG 6-bit affine quant — coherent tool-calling, verified in Osaurus runtime (replaces broken 4-bit)

7348596 verified 9 days ago

Raw

History Blame Contribute Delete

1.64 kB

	{
	"activation_func": "swiglu",
	"activation_func_fp8_input_store": false,
	"add_bias_linear": false,
	"architectures": [
	"ZayaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bias_activation_fusion": true,
	"bos_token_id": 2,
	"cca": true,
	"dtype": "bfloat16",
	"eos_token_id": 106,
	"ffn_hidden_size": 4096,
	"gated_linear_unit": true,
	"hidden_size": 2048,
	"head_dim": 128,
	"kv_channels": 128,
	"lm_head_bias": false,
	"mamba_cache_dtype": "float32",
	"max_position_embeddings": 131072,
	"model_type": "zaya",
	"moe_router_topk": 1,
	"norm_epsilon": 1e-05,
	"normalization": "RMSNorm",
	"num_attention_heads": 8,
	"num_experts": 16,
	"num_hidden_layers": 80,
	"num_key_value_heads": 2,
	"num_query_groups": 2,
	"pad_token_id": 0,
	"partial_rotary_factor": 0.5,
	"residual_in_fp32": true,
	"rope_scaling": false,
	"rope_theta": 5000000,
	"scale_residual_merge": true,
	"sliding_window": null,
	"transformers_version": "4.57.1",
	"use_cache": true,
	"vocab_size": 262272,
	"zaya_mlp_expansion": 256,
	"zaya_use_eda": true,
	"zaya_use_mod": true,
	"weight_format": "mxfp4",
	"zaya_expert_layout": "split_switch_mlp",
	"tie_word_embeddings": true,
	"quantization": {
	"bits": 6,
	"group_size": 32,
	"mode": "affine",
	"embed_bits": 8,
	"router_bits": 16,
	"expert_layout": "split_switch_mlp"
	},
	"capabilities": {
	"reasoning_parser": "qwen3",
	"tool_parser": "zaya_xml",
	"think_in_template": false,
	"supports_tools": true,
	"supports_thinking": true,
	"family": "zaya",
	"modality": "text",
	"cache_type": "hybrid"
	}
	}