Instructions to use z0n3x/gemma-4-12b-fin-grpo-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use z0n3x/gemma-4-12b-fin-grpo-v4 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("z0n3x/gemma-4-12b-fin-grpo-v4")

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 Settings
LM Studio

How to use z0n3x/gemma-4-12b-fin-grpo-v4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "z0n3x/gemma-4-12b-fin-grpo-v4"

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": "z0n3x/gemma-4-12b-fin-grpo-v4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use z0n3x/gemma-4-12b-fin-grpo-v4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "z0n3x/gemma-4-12b-fin-grpo-v4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "z0n3x/gemma-4-12b-fin-grpo-v4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "z0n3x/gemma-4-12b-fin-grpo-v4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use z0n3x/gemma-4-12b-fin-grpo-v4 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 "z0n3x/gemma-4-12b-fin-grpo-v4"

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 z0n3x/gemma-4-12b-fin-grpo-v4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use z0n3x/gemma-4-12b-fin-grpo-v4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "z0n3x/gemma-4-12b-fin-grpo-v4"

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 "z0n3x/gemma-4-12b-fin-grpo-v4" \
  --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"

z0n3x commited on Jun 15

Commit

f2b2cb2

verified ·

1 Parent(s): a0fdfd4

model card: document default <think> reasoning + LM Studio reasoning tags + text-only note

Browse files

Files changed (1) hide show

README.md +12 -0

README.md CHANGED Viewed

@@ -104,6 +104,18 @@ prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
 print(generate(model, tokenizer, prompt=prompt, max_tokens=800))
 ```
 > **Note on loading:** these are brand-new Gemma 4 "unified" weights. With some `mlx-lm`
 > versions you may need a small load-time shim that (a) resolves `model_type: gemma4` and
 > (b) drops unused multimodal tensors. This is a **text-only** checkpoint.

 print(generate(model, tokenizer, prompt=prompt, max_tokens=800))
 ```
+### Thinking / reasoning
+The chat template **defaults to a reasoning system prompt**, so the model produces
+`<think> … </think>` then the answer **out of the box** — you don't need to pass a system
+message (pass your own to override it). The reasoning markers are `<think>` / `</think>`
+(this model was trained on those tags, not Gemma's native `<|channel>thought` format).
+- **LM Studio:** set the reasoning / "thinking" section tags to `<think>` (start) and
+  `</think>` (end) to fold the chain-of-thought into a collapsible block.
+- **Text-only:** the base Gemma 4 vision/audio weights were dropped during fine-tuning, so
+  this checkpoint is **not multimodal** — by design (Fin-R1 is a text recipe).
 > **Note on loading:** these are brand-new Gemma 4 "unified" weights. With some `mlx-lm`
 > versions you may need a small load-time shim that (a) resolves `model_type: gemma4` and
 > (b) drops unused multimodal tensors. This is a **text-only** checkpoint.