Image-Text-to-Text
MLX
Safetensors
gemma4_unified
apple-silicon
multimodal
text-classification
image-classification
typed-decision
conversational
4-bit precision
Instructions to use Ruiruiz30/Jev-Omni-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Ruiruiz30/Jev-Omni-MLX-4bit 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("Ruiruiz30/Jev-Omni-MLX-4bit") config = load_config("Ruiruiz30/Jev-Omni-MLX-4bit") # 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
- Pi
How to use Ruiruiz30/Jev-Omni-MLX-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Ruiruiz30/Jev-Omni-MLX-4bit"
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": "Ruiruiz30/Jev-Omni-MLX-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use Ruiruiz30/Jev-Omni-MLX-4bit 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 "Ruiruiz30/Jev-Omni-MLX-4bit"
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 Ruiruiz30/Jev-Omni-MLX-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Ruiruiz30/Jev-Omni-MLX-4bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Ruiruiz30/Jev-Omni-MLX-4bit"
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 "Ruiruiz30/Jev-Omni-MLX-4bit" \ --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"
add benchmark and calibration charts to model card
Browse files- README.md +21 -0
- assets/jevbench-accuracy.svg +42 -0
- assets/jevbench-calibration.svg +57 -0
- assets/local-latency.svg +29 -0
README.md
CHANGED
|
@@ -42,6 +42,21 @@ The first request includes MLX graph and memory warm-up. On the same machine, a
|
|
| 42 |
|
| 43 |
The published Jev-Omni H200 numbers are not transferable to this Mac mini. This model card reports local measurements only.
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
## Validation
|
| 46 |
|
| 47 |
- Upstream unified verification cases: 4/4 argmax decisions matched after 4-bit conversion.
|
|
@@ -89,6 +104,12 @@ Omit `--calibration` to inspect the raw quantized probabilities. The included ca
|
|
| 89 |
- [`calibration.json`](calibration.json) is the small runtime file consumed by `--calibration`.
|
| 90 |
- The benchmark runner and raw checkpoints remain in the source project so the long DecisionBench run can be resumed without putting the full benchmark text into this model repository.
|
| 91 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
## Local conversion code
|
| 93 |
|
| 94 |
`omni_mlx/convert.py` contains the conversion path used for this release. The original unquantized checkpoint is not bundled here; it can be obtained from the upstream repository under its own license and terms.
|
|
|
|
| 42 |
|
| 43 |
The published Jev-Omni H200 numbers are not transferable to this Mac mini. This model card reports local measurements only.
|
| 44 |
|
| 45 |
+

|
| 46 |
+
|
| 47 |
+
## Results
|
| 48 |
+
|
| 49 |
+
The public JevBench files were evaluated with the same typed-choice mapping used by the runtime. Temperature scaling changes probabilities only; it does not change the selected option.
|
| 50 |
+
|
| 51 |
+
| Benchmark | Accuracy / state macro | Micro accuracy | ECE-10 |
|
| 52 |
+
|---|---:|---:|---:|
|
| 53 |
+
| JevBench public · 231 decisions | **87.88%** | **87.88%** | 0.04497 raw / **0.03069** scaled |
|
| 54 |
+
| DecisionBench Medium · 293 questions | — | — | Full run not published |
|
| 55 |
+
|
| 56 |
+

|
| 57 |
+
|
| 58 |
+
The JevBench result is our local public-set measurement, not a claim that the 4-bit MLX conversion reproduces the upstream card's protocol. The upstream [Jev-Omni card](https://huggingface.co/akhilaaa3/Jev-Omni) reports its own merged-model result separately. Dataset revisions, item filtering and scoring splits must match before comparing the numbers.
|
| 59 |
+
|
| 60 |
## Validation
|
| 61 |
|
| 62 |
- Upstream unified verification cases: 4/4 argmax decisions matched after 4-bit conversion.
|
|
|
|
| 104 |
- [`calibration.json`](calibration.json) is the small runtime file consumed by `--calibration`.
|
| 105 |
- The benchmark runner and raw checkpoints remain in the source project so the long DecisionBench run can be resumed without putting the full benchmark text into this model repository.
|
| 106 |
|
| 107 |
+
## Calibration
|
| 108 |
+
|
| 109 |
+
Temperature scaling was fit on 116 even-indexed public JevBench rows and checked on 115 odd-indexed rows. The fitted temperature is `T=1.11516790625`. On the full public set, ECE-10 moves from `0.04497` to `0.03069`; on the held-out split it moves from `0.06261` to `0.06774`. This is a transparent post-hoc calibration file, not a guarantee of calibrated confidence on game footage.
|
| 110 |
+
|
| 111 |
+

|
| 112 |
+
|
| 113 |
## Local conversion code
|
| 114 |
|
| 115 |
`omni_mlx/convert.py` contains the conversion path used for this release. The original unquantized checkpoint is not bundled here; it can be obtained from the upstream repository under its own license and terms.
|
assets/jevbench-accuracy.svg
ADDED
|
|
assets/jevbench-calibration.svg
ADDED
|
|
assets/local-latency.svg
ADDED
|
|