Instructions to use bernardw/qwen3-4b-codereview-taid with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bernardw/qwen3-4b-codereview-taid 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("bernardw/qwen3-4b-codereview-taid")

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 bernardw/qwen3-4b-codereview-taid with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "bernardw/qwen3-4b-codereview-taid"

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": "bernardw/qwen3-4b-codereview-taid"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bernardw/qwen3-4b-codereview-taid 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 "bernardw/qwen3-4b-codereview-taid"

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 bernardw/qwen3-4b-codereview-taid

Run Hermes

hermes

OpenClaw new

How to use bernardw/qwen3-4b-codereview-taid with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "bernardw/qwen3-4b-codereview-taid"

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 "bernardw/qwen3-4b-codereview-taid" \
  --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 bernardw/qwen3-4b-codereview-taid with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "bernardw/qwen3-4b-codereview-taid"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "bernardw/qwen3-4b-codereview-taid"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "bernardw/qwen3-4b-codereview-taid",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

qwen3-4b-codereview-taid / README.md

bernardw

Upload README.md with huggingface_hub

187a952 verified 13 days ago

preview code

Raw

History Blame

1.9 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen3-4B
	tags: [code-review, distillation, taid, knowledge-distillation, mlx, qwen3]
	language: [en]
	pipeline_tag: text-generation
	---

	# Qwen3-4B Code-Review (TAID, from Qwen3-8B)

	A Qwen3-4B student distilled (forward-KL logit-level KD / TAID) from the Qwen3-8B
	teacher to emit structured JSON code-review findings.

	- Held-out F1: 0.562 on `eval_set_100` (precision 0.517 / recall 0.616).
	- Best model in the project. Beats the prior best single student (0.509) by +0.053 and the best weight-space merge (0.535) by +0.027, with the highest precision AND recall of any student.
	- License: Apache-2.0 (pure Qwen3 lineage -- no third-party teacher-license strings).

	Method. Cached-logit knowledge distillation on Apple MLX. The Qwen3-8B teacher (8-bit) reviews
	each chunk once (thinking disabled -> clean JSON targets); we cache its top-k=50 logits over the
	response positions and train a LoRA student (rank 16 / 16 layers, lr 1e-4, seq 768, 30 epochs) toward
	that distribution (forward-KL / TAID, native temperature), then fuse. All Qwen3 sizes share a tokenizer,
	so logit-level distillation from the 8B works directly.

	Prompt contract. Given a numbered code chunk, emit one JSON object
	`{"findings":[{category, subtype, severity, confidence, title, body, evidence, line}]}`; `evidence` is a
	verbatim source substring, `line` 1-based. Held-out eval: `eval_set_100` (100 labeled chunks, py/js/c/go).

	Why this teacher. The project's dominant finding was that teacher quality is the single biggest
	lever. Swapping the Qwen2.5-Coder-7B / Gemma-9B teachers (best prior student F1 0.509, best merge 0.535)
	for Qwen3-8B produced a new best on the first attempt, at both sizes -- while a dozen objective/capacity
	tricks (reverse-KL, temperature, hybrid loss, LoRA depth, on-policy GKD) all failed to move the ceiling.