Instructions to use PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16 with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16")
config = load_config("PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16"

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": "PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16 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 "PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16"

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 PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16"

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 "PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16" \
  --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"

PocketAiHub commited on 28 days ago

Commit

6ef158d

verified ·

1 Parent(s): fbc7b52

Clarify purpose and responsible-use framing

Browse files

Files changed (3) hide show

README.md +16 -12
artifact-manifest.json +4 -4
release-manifest.json +4 -4

README.md CHANGED Viewed

@@ -21,13 +21,17 @@ The original model is by the Ornith team. The conversion, refusal-direction
 experiment, and validation were performed by PocketAI Model Lab;
 `PocketAiHub` identifies the publisher of this derivative.
-## Important safety notice
-This checkpoint was deliberately modified to suppress learned refusal
-behavior. It may produce harmful, illegal, offensive, deceptive, or dangerously
-incorrect content more readily than the upstream model. Abliteration is not
-truthfulness training, a capability improvement, or a guarantee of universal
-compliance. Independently evaluate and constrain outputs for your use case.
 ## Release family
@@ -54,8 +58,8 @@ compliance. Independently evaluate and constrain outputs for your use case.
 | Gate | Result |
 | --- | ---: |
-| Harmful explicit-refusal phrase flags | 0/100 |
-| Benign explicit-refusal phrase flags | 0/100 |
 | Medium capability suite | 71/80 |
 | Runtime smoke | passed |
@@ -64,10 +68,10 @@ following, coding, structured output, multilingual output, context
 comprehension, and general coherence.
-The refusal scorer is phrase based. Manual review found semantic redirects that
-it did not flag, so 0/100 phrase flags does not mean fully uncensored or
-universally compliant. The 256-token runs are early-refusal screens rather than
-complete long-answer evaluations.
 See [`abliteration-manifest.json`](./abliteration-manifest.json) and

 experiment, and validation were performed by PocketAI Model Lab;
 `PocketAiHub` identifies the publisher of this derivative.
+## Purpose and responsible use
+This experimental derivative studies whether learned refusal behavior can be
+reduced while retaining general capability. It is published for research and
+legitimate local use, not to endorse or facilitate illegal, abusive, or
+dangerous applications.
+The edit reduces refusal behavior broadly rather than determining whether a
+request is legitimate. Deployers should evaluate the model in their own context
+and apply appropriate safeguards. Abliteration is not truthfulness training, a
+capability improvement, or a guarantee of universal compliance.
 ## Release family
 | Gate | Result |
 | --- | ---: |
+| Refusal-targeted explicit-refusal phrase flags | 0/100 |
+| Benign-control explicit-refusal phrase flags | 0/100 |
 | Medium capability suite | 71/80 |
 | Runtime smoke | passed |
 comprehension, and general coherence.
+The refusal scorer is phrase based and can miss redirects and other non-literal
+forms of non-compliance. Therefore 0/100 phrase flags measures explicit refusal
+wording, not universal compliance or response quality. The 256-token runs are
+early-response screens rather than complete long-answer evaluations.
 See [`abliteration-manifest.json`](./abliteration-manifest.json) and

artifact-manifest.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "generated_at": "2026-08-22T07:48:14.518035+00:00",
   "repository": "PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16",
   "status": "packaged-not-published",
   "visibility": "public",
@@ -16,8 +16,8 @@
     },
     {
       "path": "README.md",
-      "size_bytes": 3049,
-      "sha256": "e06fdb8fee145cadaf3ab02afd04d671977b53a317beb896fc7dfa0e4b948c1e"
     },
     {
       "path": "abliteration-manifest.json",
@@ -95,5 +95,5 @@
       "sha256": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003"
     }
   ],
-  "total_size_bytes": 18846528272
 }

 {
   "schema_version": 1,
+  "generated_at": "2026-08-22T10:57:05.667305+00:00",
   "repository": "PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16",
   "status": "packaged-not-published",
   "visibility": "public",
     },
     {
       "path": "README.md",
+      "size_bytes": 3281,
+      "sha256": "650ed03b7fb7928806c4a2d67cad87cd17cc45ddb613e831ed8d3a41e6526396"
     },
     {
       "path": "abliteration-manifest.json",
       "sha256": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003"
     }
   ],
+  "total_size_bytes": 18846528504
 }

release-manifest.json CHANGED Viewed

@@ -1,15 +1,15 @@
 {
   "schema_version": 1,
-  "generated_at": "2026-08-22T07:48:14.518141+00:00",
   "status": "packaged-not-published",
   "repository": "PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16",
   "visibility": "public",
   "variant": "mlx-bf16",
   "file_count": 19,
-  "total_size_bytes": 18846528272,
-  "artifact_manifest_sha256": "2616f59f76728f1f8e4200c3589e49e973b96f1048fd9641f7806e94c6fe8f46",
   "evidence": {
-    "README.md": "e06fdb8fee145cadaf3ab02afd04d671977b53a317beb896fc7dfa0e4b948c1e",
     "LICENSE": "1ade8ac5b311a030e098ce9e838b49443ef90923c10f291bce978e3f69702b7d",
     "abliteration-manifest.json": "309b1d6ed1de11b8c450f79c9f1df7ba7cdf709e52fa7dae9d9b2d81fb6dfb67",
     "validation-summary.json": "be7ad26ba85caf68b79fc30afad1eb2b097b114f6613df3980fb2defa921ae07"

 {
   "schema_version": 1,
+  "generated_at": "2026-08-22T10:57:05.667401+00:00",
   "status": "packaged-not-published",
   "repository": "PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-BF16",
   "visibility": "public",
   "variant": "mlx-bf16",
   "file_count": 19,
+  "total_size_bytes": 18846528504,
+  "artifact_manifest_sha256": "86807772fbf4e27ae756e557b7d6145a8df4721c6f353bbe9352605c687ce24f",
   "evidence": {
+    "README.md": "650ed03b7fb7928806c4a2d67cad87cd17cc45ddb613e831ed8d3a41e6526396",
     "LICENSE": "1ade8ac5b311a030e098ce9e838b49443ef90923c10f291bce978e3f69702b7d",
     "abliteration-manifest.json": "309b1d6ed1de11b8c450f79c9f1df7ba7cdf709e52fa7dae9d9b2d81fb6dfb67",
     "validation-summary.json": "be7ad26ba85caf68b79fc30afad1eb2b097b114f6613df3980fb2defa921ae07"