Instructions to use thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP 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("thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP")

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 thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP"

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": "thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP 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 "thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP"

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 thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP"

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 "thelogicalgate/Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP" \
  --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"

Sage-A1.5-Cybersecurity-Abliterated-MLX-8bit-MTP / abliteration_config.json

thelogicalgate

Release cybersecurity-oriented Sage-A1.5 MLX 8-bit with MoE MTP; tested in MLX-Serve

83e56c5 11 days ago

Raw History Blame Contribute Delete

5.43 kB

{
  "source": "InternScience/Sage-A1.5",
  "strength": 0.75,
  "modified_modules": [
    "language_model.model.layers.31.mlp.shared_expert.down_proj",
    "language_model.model.layers.31.mlp.switch_mlp.down_proj",
    "language_model.model.layers.31.self_attn.o_proj",
    "language_model.model.layers.30.mlp.shared_expert.down_proj",
    "language_model.model.layers.30.mlp.switch_mlp.down_proj",
    "language_model.model.layers.30.linear_attn.out_proj",
    "language_model.model.layers.29.mlp.shared_expert.down_proj",
    "language_model.model.layers.29.mlp.switch_mlp.down_proj",
    "language_model.model.layers.29.linear_attn.out_proj",
    "language_model.model.layers.28.mlp.shared_expert.down_proj",
    "language_model.model.layers.28.mlp.switch_mlp.down_proj",
    "language_model.model.layers.28.linear_attn.out_proj",
    "language_model.model.layers.27.mlp.shared_expert.down_proj",
    "language_model.model.layers.27.mlp.switch_mlp.down_proj",
    "language_model.model.layers.27.self_attn.o_proj",
    "language_model.model.layers.26.mlp.shared_expert.down_proj",
    "language_model.model.layers.26.mlp.switch_mlp.down_proj",
    "language_model.model.layers.26.linear_attn.out_proj",
    "language_model.model.layers.25.mlp.shared_expert.down_proj",
    "language_model.model.layers.25.mlp.switch_mlp.down_proj",
    "language_model.model.layers.25.linear_attn.out_proj",
    "language_model.model.layers.24.mlp.shared_expert.down_proj",
    "language_model.model.layers.24.mlp.switch_mlp.down_proj",
    "language_model.model.layers.24.linear_attn.out_proj",
    "language_model.model.layers.23.mlp.shared_expert.down_proj",
    "language_model.model.layers.23.mlp.switch_mlp.down_proj",
    "language_model.model.layers.23.self_attn.o_proj",
    "language_model.model.layers.22.mlp.shared_expert.down_proj",
    "language_model.model.layers.22.mlp.switch_mlp.down_proj",
    "language_model.model.layers.22.linear_attn.out_proj",
    "language_model.model.layers.21.mlp.shared_expert.down_proj",
    "language_model.model.layers.21.mlp.switch_mlp.down_proj",
    "language_model.model.layers.21.linear_attn.out_proj",
    "language_model.model.layers.20.mlp.shared_expert.down_proj",
    "language_model.model.layers.20.mlp.switch_mlp.down_proj",
    "language_model.model.layers.20.linear_attn.out_proj",
    "language_model.model.layers.19.mlp.shared_expert.down_proj",
    "language_model.model.layers.19.mlp.switch_mlp.down_proj",
    "language_model.model.layers.19.self_attn.o_proj",
    "language_model.model.layers.18.mlp.shared_expert.down_proj",
    "language_model.model.layers.18.mlp.switch_mlp.down_proj",
    "language_model.model.layers.18.linear_attn.out_proj",
    "language_model.model.layers.17.mlp.shared_expert.down_proj",
    "language_model.model.layers.17.mlp.switch_mlp.down_proj",
    "language_model.model.layers.17.linear_attn.out_proj",
    "language_model.model.layers.16.mlp.shared_expert.down_proj",
    "language_model.model.layers.16.mlp.switch_mlp.down_proj",
    "language_model.model.layers.16.linear_attn.out_proj",
    "language_model.model.layers.15.mlp.shared_expert.down_proj",
    "language_model.model.layers.15.mlp.switch_mlp.down_proj",
    "language_model.model.layers.15.self_attn.o_proj",
    "language_model.model.layers.14.mlp.shared_expert.down_proj",
    "language_model.model.layers.14.mlp.switch_mlp.down_proj",
    "language_model.model.layers.14.linear_attn.out_proj",
    "language_model.model.layers.13.mlp.shared_expert.down_proj",
    "language_model.model.layers.13.mlp.switch_mlp.down_proj",
    "language_model.model.layers.13.linear_attn.out_proj",
    "language_model.model.layers.12.mlp.shared_expert.down_proj",
    "language_model.model.layers.12.mlp.switch_mlp.down_proj",
    "language_model.model.layers.12.linear_attn.out_proj",
    "language_model.model.layers.11.mlp.shared_expert.down_proj",
    "language_model.model.layers.11.mlp.switch_mlp.down_proj",
    "language_model.model.layers.11.self_attn.o_proj",
    "language_model.model.layers.10.mlp.shared_expert.down_proj",
    "language_model.model.layers.10.mlp.switch_mlp.down_proj",
    "language_model.model.layers.10.linear_attn.out_proj",
    "language_model.model.layers.9.mlp.shared_expert.down_proj",
    "language_model.model.layers.9.mlp.switch_mlp.down_proj",
    "language_model.model.layers.9.linear_attn.out_proj",
    "language_model.model.layers.8.mlp.shared_expert.down_proj",
    "language_model.model.layers.8.mlp.switch_mlp.down_proj",
    "language_model.model.layers.8.linear_attn.out_proj"
  ],
  "bits": 8,
  "group_size": 64,
  "vision_preserved": true,
  "mtp_exported": true,
  "method": "single residual direction; partial norm-preserving output-weight projection; layers 8..31",
  "source_revision": "3e6b02c5e6afbc481fd4556baca8e6009f26d696",
  "selected_direction_layer": 17,
  "calibration": {
    "contrast_dataset": "mlabonne/harmful_behaviors",
    "control_dataset": "mlabonne/harmless_alpaca",
    "samples_per_dataset": 128,
    "fit_per_dataset": 96,
    "selection_per_dataset": 32,
    "shuffle_seed": 42,
    "domain_specific": false
  },
  "release_scope": "Cybersecurity-oriented intended use and evaluation; calibration is general contrast data; effects are not technically confined to cybersecurity.",
  "build_versions": {
    "mlx": "0.32.4",
    "mlx-vlm": "0.7.10",
    "transformers": "5.20.2",
    "numpy": "2.5.4"
  }
}

	{
	"source": "InternScience/Sage-A1.5",
	"strength": 0.75,
	"modified_modules": [
	"language_model.model.layers.31.mlp.shared_expert.down_proj",
	"language_model.model.layers.31.mlp.switch_mlp.down_proj",
	"language_model.model.layers.31.self_attn.o_proj",
	"language_model.model.layers.30.mlp.shared_expert.down_proj",
	"language_model.model.layers.30.mlp.switch_mlp.down_proj",
	"language_model.model.layers.30.linear_attn.out_proj",
	"language_model.model.layers.29.mlp.shared_expert.down_proj",
	"language_model.model.layers.29.mlp.switch_mlp.down_proj",
	"language_model.model.layers.29.linear_attn.out_proj",
	"language_model.model.layers.28.mlp.shared_expert.down_proj",
	"language_model.model.layers.28.mlp.switch_mlp.down_proj",
	"language_model.model.layers.28.linear_attn.out_proj",
	"language_model.model.layers.27.mlp.shared_expert.down_proj",
	"language_model.model.layers.27.mlp.switch_mlp.down_proj",
	"language_model.model.layers.27.self_attn.o_proj",
	"language_model.model.layers.26.mlp.shared_expert.down_proj",
	"language_model.model.layers.26.mlp.switch_mlp.down_proj",
	"language_model.model.layers.26.linear_attn.out_proj",
	"language_model.model.layers.25.mlp.shared_expert.down_proj",
	"language_model.model.layers.25.mlp.switch_mlp.down_proj",
	"language_model.model.layers.25.linear_attn.out_proj",
	"language_model.model.layers.24.mlp.shared_expert.down_proj",
	"language_model.model.layers.24.mlp.switch_mlp.down_proj",
	"language_model.model.layers.24.linear_attn.out_proj",
	"language_model.model.layers.23.mlp.shared_expert.down_proj",
	"language_model.model.layers.23.mlp.switch_mlp.down_proj",
	"language_model.model.layers.23.self_attn.o_proj",
	"language_model.model.layers.22.mlp.shared_expert.down_proj",
	"language_model.model.layers.22.mlp.switch_mlp.down_proj",
	"language_model.model.layers.22.linear_attn.out_proj",
	"language_model.model.layers.21.mlp.shared_expert.down_proj",
	"language_model.model.layers.21.mlp.switch_mlp.down_proj",
	"language_model.model.layers.21.linear_attn.out_proj",
	"language_model.model.layers.20.mlp.shared_expert.down_proj",
	"language_model.model.layers.20.mlp.switch_mlp.down_proj",
	"language_model.model.layers.20.linear_attn.out_proj",
	"language_model.model.layers.19.mlp.shared_expert.down_proj",
	"language_model.model.layers.19.mlp.switch_mlp.down_proj",
	"language_model.model.layers.19.self_attn.o_proj",
	"language_model.model.layers.18.mlp.shared_expert.down_proj",
	"language_model.model.layers.18.mlp.switch_mlp.down_proj",
	"language_model.model.layers.18.linear_attn.out_proj",
	"language_model.model.layers.17.mlp.shared_expert.down_proj",
	"language_model.model.layers.17.mlp.switch_mlp.down_proj",
	"language_model.model.layers.17.linear_attn.out_proj",
	"language_model.model.layers.16.mlp.shared_expert.down_proj",
	"language_model.model.layers.16.mlp.switch_mlp.down_proj",
	"language_model.model.layers.16.linear_attn.out_proj",
	"language_model.model.layers.15.mlp.shared_expert.down_proj",
	"language_model.model.layers.15.mlp.switch_mlp.down_proj",
	"language_model.model.layers.15.self_attn.o_proj",
	"language_model.model.layers.14.mlp.shared_expert.down_proj",
	"language_model.model.layers.14.mlp.switch_mlp.down_proj",
	"language_model.model.layers.14.linear_attn.out_proj",
	"language_model.model.layers.13.mlp.shared_expert.down_proj",
	"language_model.model.layers.13.mlp.switch_mlp.down_proj",
	"language_model.model.layers.13.linear_attn.out_proj",
	"language_model.model.layers.12.mlp.shared_expert.down_proj",
	"language_model.model.layers.12.mlp.switch_mlp.down_proj",
	"language_model.model.layers.12.linear_attn.out_proj",
	"language_model.model.layers.11.mlp.shared_expert.down_proj",
	"language_model.model.layers.11.mlp.switch_mlp.down_proj",
	"language_model.model.layers.11.self_attn.o_proj",
	"language_model.model.layers.10.mlp.shared_expert.down_proj",
	"language_model.model.layers.10.mlp.switch_mlp.down_proj",
	"language_model.model.layers.10.linear_attn.out_proj",
	"language_model.model.layers.9.mlp.shared_expert.down_proj",
	"language_model.model.layers.9.mlp.switch_mlp.down_proj",
	"language_model.model.layers.9.linear_attn.out_proj",
	"language_model.model.layers.8.mlp.shared_expert.down_proj",
	"language_model.model.layers.8.mlp.switch_mlp.down_proj",
	"language_model.model.layers.8.linear_attn.out_proj"
	],
	"bits": 8,
	"group_size": 64,
	"vision_preserved": true,
	"mtp_exported": true,
	"method": "single residual direction; partial norm-preserving output-weight projection; layers 8..31",
	"source_revision": "3e6b02c5e6afbc481fd4556baca8e6009f26d696",
	"selected_direction_layer": 17,
	"calibration": {
	"contrast_dataset": "mlabonne/harmful_behaviors",
	"control_dataset": "mlabonne/harmless_alpaca",
	"samples_per_dataset": 128,
	"fit_per_dataset": 96,
	"selection_per_dataset": 32,
	"shuffle_seed": 42,
	"domain_specific": false
	},
	"release_scope": "Cybersecurity-oriented intended use and evaluation; calibration is general contrast data; effects are not technically confined to cybersecurity.",
	"build_versions": {
	"mlx": "0.32.4",
	"mlx-vlm": "0.7.10",
	"transformers": "5.20.2",
	"numpy": "2.5.4"
	}
	}