Instructions to use OsaurusAI/Hy3-preview-JANGTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/Hy3-preview-JANGTQ 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/Hy3-preview-JANGTQ")

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
LM Studio

Pi new

How to use OsaurusAI/Hy3-preview-JANGTQ 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/Hy3-preview-JANGTQ"

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/Hy3-preview-JANGTQ"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OsaurusAI/Hy3-preview-JANGTQ 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/Hy3-preview-JANGTQ"

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/Hy3-preview-JANGTQ

Run Hermes

hermes

MLX LM

How to use OsaurusAI/Hy3-preview-JANGTQ 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/Hy3-preview-JANGTQ"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OsaurusAI/Hy3-preview-JANGTQ"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OsaurusAI/Hy3-preview-JANGTQ",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Osaurus-AI commited on 1 day ago

Commit

f9f278b

verified ·

1 Parent(s): f8c5df9

Update runtime support matrix: vmlx-swift-lm Hy3 now supported

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -140,6 +140,6 @@ attribute count it modified.
 | Surface | Status |
 |---|---|
 | `jang-tools` Python (`load_jangtq_model`) | ✅ working — this README's load snippet |
-| `vmlx_engine` Python via re-export | pending — `vmlx_engine.loaders.load_jangtq_hy3` should re-export `jang_tools.hy3.runtime.load_hy3_model` |
-| `vmlx-swift-lm` Swift | ❌ pending — `LLMModelFactory.dispatchHy3Unsupported` currently throws; needs new `Hy3.swift` model class + JANGTQ Swift dispatch |
 | MTP speculative decode | preserved-disabled — weights present in bundle, accept/reject loop not yet implemented in any JANG runtime |

 | Surface | Status |
 |---|---|
 | `jang-tools` Python (`load_jangtq_model`) | ✅ working — this README's load snippet |
+| `vmlx-swift-lm` Swift | ✅ working — `Libraries/MLXLLM/Models/Hy3.swift` + JANGTQ codebook dispatch. Same family path that ships ZAYA and Bailing/Ling. |
+| `vmlx_engine` Python via re-export | pending — `vmlx_engine.loaders.load_jangtq_hy3` re-export of `jang_tools.hy3.runtime.load_hy3_model` not yet wired |
 | MTP speculative decode | preserved-disabled — weights present in bundle, accept/reject loop not yet implemented in any JANG runtime |