Instructions to use wsgpolar/Anura-R1-Ultra with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wsgpolar/Anura-R1-Ultra 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("wsgpolar/Anura-R1-Ultra")
config = load_config("wsgpolar/Anura-R1-Ultra")

# 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 wsgpolar/Anura-R1-Ultra with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "wsgpolar/Anura-R1-Ultra"

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": "wsgpolar/Anura-R1-Ultra"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use wsgpolar/Anura-R1-Ultra 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 "wsgpolar/Anura-R1-Ultra"

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 wsgpolar/Anura-R1-Ultra

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use wsgpolar/Anura-R1-Ultra with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "wsgpolar/Anura-R1-Ultra"

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 "wsgpolar/Anura-R1-Ultra" \
  --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"

Anura-R1-Ultra / training /adapters /dev-test /adapter_config.json

wsgpolar

Back up training/adapters

fcbae76 verified 23 days ago

Raw History Blame Contribute Delete

3.01 kB

{
  "fine_tune_type": "lora",
  "lora_parameters": {
    "dropout": 0.05,
    "keys": [
      "language_model.model.layers.23.mlp.up_proj",
      "language_model.model.layers.23.mlp.down_proj",
      "language_model.model.layers.23.mlp.gate_proj",
      "language_model.model.layers.23.self_attn.o_proj",
      "language_model.model.layers.23.self_attn.v_proj",
      "language_model.model.layers.23.self_attn.k_proj",
      "language_model.model.layers.23.self_attn.q_proj",
      "language_model.model.layers.22.mlp.up_proj",
      "language_model.model.layers.22.mlp.down_proj",
      "language_model.model.layers.22.mlp.gate_proj",
      "language_model.model.layers.22.linear_attn.out_proj",
      "language_model.model.layers.22.linear_attn.in_proj_z",
      "language_model.model.layers.22.linear_attn.in_proj_qkv",
      "language_model.model.layers.21.mlp.up_proj",
      "language_model.model.layers.21.mlp.down_proj",
      "language_model.model.layers.21.mlp.gate_proj",
      "language_model.model.layers.21.linear_attn.out_proj",
      "language_model.model.layers.21.linear_attn.in_proj_z",
      "language_model.model.layers.21.linear_attn.in_proj_qkv",
      "language_model.model.layers.20.mlp.up_proj",
      "language_model.model.layers.20.mlp.down_proj",
      "language_model.model.layers.20.mlp.gate_proj",
      "language_model.model.layers.20.linear_attn.out_proj",
      "language_model.model.layers.20.linear_attn.in_proj_z",
      "language_model.model.layers.20.linear_attn.in_proj_qkv",
      "language_model.model.layers.19.mlp.up_proj",
      "language_model.model.layers.19.mlp.down_proj",
      "language_model.model.layers.19.mlp.gate_proj",
      "language_model.model.layers.19.self_attn.o_proj",
      "language_model.model.layers.19.self_attn.v_proj",
      "language_model.model.layers.19.self_attn.k_proj",
      "language_model.model.layers.19.self_attn.q_proj",
      "language_model.model.layers.18.mlp.up_proj",
      "language_model.model.layers.18.mlp.down_proj",
      "language_model.model.layers.18.mlp.gate_proj",
      "language_model.model.layers.18.linear_attn.out_proj",
      "language_model.model.layers.18.linear_attn.in_proj_z",
      "language_model.model.layers.18.linear_attn.in_proj_qkv",
      "language_model.model.layers.17.mlp.up_proj",
      "language_model.model.layers.17.mlp.down_proj",
      "language_model.model.layers.17.mlp.gate_proj",
      "language_model.model.layers.17.linear_attn.out_proj",
      "language_model.model.layers.17.linear_attn.in_proj_z",
      "language_model.model.layers.17.linear_attn.in_proj_qkv",
      "language_model.model.layers.16.mlp.up_proj",
      "language_model.model.layers.16.mlp.down_proj",
      "language_model.model.layers.16.mlp.gate_proj",
      "language_model.model.layers.16.linear_attn.out_proj",
      "language_model.model.layers.16.linear_attn.in_proj_z",
      "language_model.model.layers.16.linear_attn.in_proj_qkv"
    ],
    "rank": 16,
    "scale": 2.0
  },
  "num_layers": -1
}

	{
	"fine_tune_type": "lora",
	"lora_parameters": {
	"dropout": 0.05,
	"keys": [
	"language_model.model.layers.23.mlp.up_proj",
	"language_model.model.layers.23.mlp.down_proj",
	"language_model.model.layers.23.mlp.gate_proj",
	"language_model.model.layers.23.self_attn.o_proj",
	"language_model.model.layers.23.self_attn.v_proj",
	"language_model.model.layers.23.self_attn.k_proj",
	"language_model.model.layers.23.self_attn.q_proj",
	"language_model.model.layers.22.mlp.up_proj",
	"language_model.model.layers.22.mlp.down_proj",
	"language_model.model.layers.22.mlp.gate_proj",
	"language_model.model.layers.22.linear_attn.out_proj",
	"language_model.model.layers.22.linear_attn.in_proj_z",
	"language_model.model.layers.22.linear_attn.in_proj_qkv",
	"language_model.model.layers.21.mlp.up_proj",
	"language_model.model.layers.21.mlp.down_proj",
	"language_model.model.layers.21.mlp.gate_proj",
	"language_model.model.layers.21.linear_attn.out_proj",
	"language_model.model.layers.21.linear_attn.in_proj_z",
	"language_model.model.layers.21.linear_attn.in_proj_qkv",
	"language_model.model.layers.20.mlp.up_proj",
	"language_model.model.layers.20.mlp.down_proj",
	"language_model.model.layers.20.mlp.gate_proj",
	"language_model.model.layers.20.linear_attn.out_proj",
	"language_model.model.layers.20.linear_attn.in_proj_z",
	"language_model.model.layers.20.linear_attn.in_proj_qkv",
	"language_model.model.layers.19.mlp.up_proj",
	"language_model.model.layers.19.mlp.down_proj",
	"language_model.model.layers.19.mlp.gate_proj",
	"language_model.model.layers.19.self_attn.o_proj",
	"language_model.model.layers.19.self_attn.v_proj",
	"language_model.model.layers.19.self_attn.k_proj",
	"language_model.model.layers.19.self_attn.q_proj",
	"language_model.model.layers.18.mlp.up_proj",
	"language_model.model.layers.18.mlp.down_proj",
	"language_model.model.layers.18.mlp.gate_proj",
	"language_model.model.layers.18.linear_attn.out_proj",
	"language_model.model.layers.18.linear_attn.in_proj_z",
	"language_model.model.layers.18.linear_attn.in_proj_qkv",
	"language_model.model.layers.17.mlp.up_proj",
	"language_model.model.layers.17.mlp.down_proj",
	"language_model.model.layers.17.mlp.gate_proj",
	"language_model.model.layers.17.linear_attn.out_proj",
	"language_model.model.layers.17.linear_attn.in_proj_z",
	"language_model.model.layers.17.linear_attn.in_proj_qkv",
	"language_model.model.layers.16.mlp.up_proj",
	"language_model.model.layers.16.mlp.down_proj",
	"language_model.model.layers.16.mlp.gate_proj",
	"language_model.model.layers.16.linear_attn.out_proj",
	"language_model.model.layers.16.linear_attn.in_proj_z",
	"language_model.model.layers.16.linear_attn.in_proj_qkv"
	],
	"rank": 16,
	"scale": 2.0
	},
	"num_layers": -1
	}