Image-Text-to-Text
MLX
Safetensors
English
Chinese
hy_v4_flash
quantized
hy4-flash
Mixture of Experts
multimodal
conversational
Instructions to use Xylolabs/Hy4-flash-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Xylolabs/Hy4-flash-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("Xylolabs/Hy4-flash-MLX-4bit") config = load_config("Xylolabs/Hy4-flash-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 Xylolabs/Hy4-flash-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 "Xylolabs/Hy4-flash-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": "Xylolabs/Hy4-flash-MLX-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use Xylolabs/Hy4-flash-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 "Xylolabs/Hy4-flash-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 Xylolabs/Hy4-flash-MLX-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Xylolabs/Hy4-flash-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 "Xylolabs/Hy4-flash-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 "Xylolabs/Hy4-flash-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"
Card: add the KL row, drop the greedy-equality sentence
Browse files
README.md
CHANGED
|
@@ -55,6 +55,14 @@ tags:
|
|
| 55 |
| Engram tables | as in the base model, in memory-mapped files |
|
| 56 |
| DFly2 drafter | bf16 |
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
## How to run
|
| 59 |
|
| 60 |
Download the repository, install `mlx-lm`, and run the chat command from the model folder:
|
|
@@ -70,7 +78,6 @@ python -m hy4_mlx.chat --model . # interactive chat
|
|
| 70 |
|
| 71 |
- Keep the folder on a local SSD: the Engram files are read at random while generating.
|
| 72 |
- The reasoning effort is `no_think`, `high` or `max`.
|
| 73 |
-
- Decoding with the DFly2 drafter checks each draft greedily, so the output equals plain greedy decoding.
|
| 74 |
|
| 75 |
## How this was made
|
| 76 |
|
|
|
|
| 55 |
| Engram tables | as in the base model, in memory-mapped files |
|
| 56 |
| DFly2 drafter | bf16 |
|
| 57 |
|
| 58 |
+
## Accuracy
|
| 59 |
+
|
| 60 |
+
Mean KL and same top-1 against the BF16 model (the BF16 GGUF trunk with its Engram file in llama.cpp), on 24 chunks of 512 tokens of wikitext-2, measured with MLX 0.32.4 on its CUDA backend and bf16 activations:
|
| 61 |
+
|
| 62 |
+
| Model | Mean KL vs BF16 | Same top-1 vs BF16 |
|
| 63 |
+
|---|---|---|
|
| 64 |
+
| Hy4-flash-MLX-4bit | 0.3066 | 82.8% |
|
| 65 |
+
|
| 66 |
## How to run
|
| 67 |
|
| 68 |
Download the repository, install `mlx-lm`, and run the chat command from the model folder:
|
|
|
|
| 78 |
|
| 79 |
- Keep the folder on a local SSD: the Engram files are read at random while generating.
|
| 80 |
- The reasoning effort is `no_think`, `high` or `max`.
|
|
|
|
| 81 |
|
| 82 |
## How this was made
|
| 83 |
|