Instructions to use atakle/socratic-tutor-rewriter-v4-1.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use atakle/socratic-tutor-rewriter-v4-1.7b 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("atakle/socratic-tutor-rewriter-v4-1.7b")

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 atakle/socratic-tutor-rewriter-v4-1.7b with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "atakle/socratic-tutor-rewriter-v4-1.7b"

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": "atakle/socratic-tutor-rewriter-v4-1.7b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use atakle/socratic-tutor-rewriter-v4-1.7b 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 "atakle/socratic-tutor-rewriter-v4-1.7b"

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 atakle/socratic-tutor-rewriter-v4-1.7b

Run Hermes

hermes

OpenClaw new

How to use atakle/socratic-tutor-rewriter-v4-1.7b with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "atakle/socratic-tutor-rewriter-v4-1.7b"

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 "atakle/socratic-tutor-rewriter-v4-1.7b" \
  --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"

MLX LM

How to use atakle/socratic-tutor-rewriter-v4-1.7b with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "atakle/socratic-tutor-rewriter-v4-1.7b"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "atakle/socratic-tutor-rewriter-v4-1.7b"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "atakle/socratic-tutor-rewriter-v4-1.7b",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Socratic Tutor Rewriter (v4) — Qwen3-1.7B (MLX)

Rewrites a flagged (leaky) tutor message into a safe, operation-free Socratic hint — never states the answer or the next step the student must take; asks one calibrated guiding question. It is the rewriter stage of a two-model guardrail (judge → rewriter); fed by atakle/socratic-tutor-judge-v9-1.7b.

Results (held-out n=60; LLM leak-detector + cross-family jury)

Key-step leak rate under the sharpened detector (leak = states the answer / takes the next step / corrects the student without nudging):

model	key-step leak (lower = safer)
base Qwen3-1.7B	38.3%
this model (rewrite_v4)	6.7%
claude-sonnet-5	6.7%
gpt-4.1	10.0%
gpt-4o	11.7%
gpt-5.6	11.7%

Safest tier of every model tested — ties the best frontier (sonnet-5) and beats gpt-5.6/4o/4.1 — at 1.7B, running locally. Not vaguer, either (longest median hint of the small models).

Usage (MLX)

from mlx_lm import load, generate
model, tok = load("atakle/socratic-tutor-rewriter-v4-1.7b")
# System prompt = the project's rewrite-task prompt (split_common.REWRITE_SYSTEM);
# user turn = the flagged candidate + its verdict + the flag reason.
# Output: a single plain-text Socratic hint (no JSON).

Trained via QLoRA (rank 16) on atakle/socratic-tutor-data — human-anchored, leak-validated targets (strict "never name the operation"). Base: Qwen3-1.7B (Apache-2.0).