Instructions to use jaigouk/qwen3-4b-german-teacher-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jaigouk/qwen3-4b-german-teacher-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="jaigouk/qwen3-4b-german-teacher-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jaigouk/qwen3-4b-german-teacher-v1")
model = AutoModelForCausalLM.from_pretrained("jaigouk/qwen3-4b-german-teacher-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use jaigouk/qwen3-4b-german-teacher-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jaigouk/qwen3-4b-german-teacher-v1",
	filename="qwen3-german-teacher-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jaigouk/qwen3-4b-german-teacher-v1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M

Use Docker

docker model run hf.co/jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M

LM Studio
Jan

vLLM

How to use jaigouk/qwen3-4b-german-teacher-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jaigouk/qwen3-4b-german-teacher-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jaigouk/qwen3-4b-german-teacher-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M

SGLang

How to use jaigouk/qwen3-4b-german-teacher-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "jaigouk/qwen3-4b-german-teacher-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jaigouk/qwen3-4b-german-teacher-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "jaigouk/qwen3-4b-german-teacher-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jaigouk/qwen3-4b-german-teacher-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use jaigouk/qwen3-4b-german-teacher-v1 with Ollama:
```
ollama run hf.co/jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M
```

Unsloth Studio

How to use jaigouk/qwen3-4b-german-teacher-v1 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jaigouk/qwen3-4b-german-teacher-v1 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jaigouk/qwen3-4b-german-teacher-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jaigouk/qwen3-4b-german-teacher-v1 to start chatting

How to use jaigouk/qwen3-4b-german-teacher-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jaigouk/qwen3-4b-german-teacher-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M

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 jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use jaigouk/qwen3-4b-german-teacher-v1 with Docker Model Runner:
```
docker model run hf.co/jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M
```

Lemonade

How to use jaigouk/qwen3-4b-german-teacher-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jaigouk/qwen3-4b-german-teacher-v1:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-4b-german-teacher-v1-Q4_K_M

List all available models

lemonade list

Qwen3-4B German Teacher

A finetuned Qwen3-4B model specialized for German language teaching at A1-B1 CEFR levels. This model excels at:

Grammar Error Detection: Identifying grammatical mistakes in German sentences
Error Correction: Providing correct forms with clear explanations
Grammar Judgment: Binary classification of sentence grammaticality (CoLA-style)
Teaching Explanations: Clear, learner-friendly explanations of German grammar rules

Model Details

Property	Value
Base Model	Qwen/Qwen3-4B
Parameters	4B
Training Method	SFT (Supervised Fine-Tuning) with LoRA
LoRA Rank	32
LoRA Alpha	64
Training Epochs	2
Learning Rate	2e-4
Context Length	4096 tokens

Performance

Evaluated on a custom German grammar benchmark:

Metric	Score	Description
CoLA MCC	0.721	Matthews Correlation Coefficient for grammaticality judgment
GEC F1	0.349	Macro F1 for grammar error correction
Generation Quality	3.99/5.0	Human-evaluated response quality
Overall Score	0.633	Weighted composite score

Benchmark Comparison

Comparison with SmolLM3-German-V6 (3B parameters, Q4 quantized):

Metric	Qwen3 German Teacher (4B)	SmolLM3-German-V6 (3B)	Improvement
CoLA MCC	0.721	0.624	+15.5%
GEC F1	0.349	0.145	+140.7%
Generation Quality	3.99	3.19	+25.1%
Overall Score	0.633	0.492	+28.7%

Key advantages of this model:

Superior grammaticality judgment: 15.5% higher CoLA MCC score
Much better error correction: 2.4x better GEC F1 score
Higher quality responses: 0.8 points higher on 5-point scale

Training Data

The model was trained on ~9,000 examples with the following composition:

Category	Percentage	Purpose
Grammar Correction	35%	Error correction patterns
Grammar Judgment	25%	CoLA-style "Is this correct?" examples
Structured Teaching	20%	Verb conjugations, grammar explanations
General Conversation	20%	Fluency preservation

Key Training Focus Areas

haben/sein auxiliary verbs: Movement verbs require "sein" (e.g., "Ich bin gefahren" not "Ich habe gefahren")
Article gender (der/die/das)
Case usage (Nominativ, Akkusativ, Dativ, Genitiv)
Word order in German sentences

Usage

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("jaigouk/qwen3-4b-german-teacher")
tokenizer = AutoTokenizer.from_pretrained("jaigouk/qwen3-4b-german-teacher")

messages = [
    {"role": "system", "content": "Du bist ein freundlicher Deutschlehrer für A1-B1 Lernende."},
    {"role": "user", "content": "Is this German sentence correct? 'Ich habe nach Berlin gefahren.'"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

With Ollama (GGUF)

Download the GGUF file: qwen3-german-teacher-Q4_K_M.gguf
Create a Modelfile:

FROM ./qwen3-german-teacher-Q4_K_M.gguf

TEMPLATE """{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
<think>

</think>

{{ .Response }}<|im_end|>
"""

PARAMETER stop "<|im_end|>"
PARAMETER stop "<|endoftext|>"
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER num_ctx 4096

SYSTEM """Du bist ein freundlicher Deutschlehrer für A1-B1 Lernende. Erkläre Grammatikfehler klar und einfach. Beurteile grammatische Korrektheit sorgfältig."""

Create and run:

ollama create qwen3-german-teacher -f Modelfile
ollama run qwen3-german-teacher "Is 'Ich habe nach Berlin gefahren' correct?"

Example Interactions

Grammar Error Detection

User: Is this German sentence grammatically correct? "Ich habe nach Berlin gefahren."

Model: No, this sentence is incorrect. The verb "fahren" describes movement from one place to another, so it requires "sein" as the auxiliary verb, not "haben".

Correct: "Ich bin nach Berlin gefahren."

Grammar Explanation

User: Explain when to use "sein" vs "haben" in the Perfekt tense.

Model: In German, most verbs use "haben" in the Perfekt tense, but verbs that describe:

Movement from A to B: gehen, fahren, fliegen, kommen, laufen
Change of state: aufwachen, einschlafen, sterben, werden

These verbs use "sein" instead. For example:

Ich bin nach Hause gegangen. (movement)
Er ist eingeschlafen. (change of state)

Conjugation Help

User: Conjugate "sein" in present tense.

Model: Here is the conjugation of "sein" (to be) in present tense:

Person	Conjugation
ich	bin
du	bist
er/sie/es	ist
wir	sind
ihr	seid
sie/Sie	sind

Limitations

Optimized for A1-B1 level German; may oversimplify advanced grammar concepts
Focused on grammar teaching; not designed for creative writing or translation
Best performance with clear, focused grammar questions

Training Methodology

Research-Informed Approach

This model was developed using insights from recent research on instruction-tuning and continual learning:

GRAPE Data Selection

Based on the GRAPE paper (Feb 2025):

"Instructions paired with responses sampled from other LLMs are often out of the distribution of the target model, which can lead to diminishing returns and even hurt performance"

Key insight: Rather than using responses generated by larger models (GPT-4, Claude), we curated training examples that align with Qwen3's natural output distribution. This prevents the model from learning patterns it cannot reliably reproduce.

CoLA-Style Judgment Training

The breakthrough in V4 was adding 25% explicit grammaticality judgment examples. This teaches the model to reason about correctness rather than just generate correct text:

User: Ist der Satz grammatisch korrekt? "Der Frau ist schön."
Assistant: Nein, der Satz ist nicht korrekt.
Fehler: "Der" ist maskulin, aber "Frau" ist feminin.
Korrektur: "Die Frau ist schön."

Lessons from EWC/Fisher Information Research

From arXiv:2502.11756 on Fisher Information computation:

EXACT computation outperforms approximations
Minimum 500 samples for reliable Fisher estimation
Device consistency (GPU-only) is critical

These insights from our earlier SmolLM3 experiments (V5/V6 with Elastic Weight Consolidation) informed our dataset composition decisions for Qwen3-V4.

Training Details

Multi-Stage Finetuning: Lessons Learned

This project was inspired by the 3-stage finetuning approach described in MiroThinker (arXiv:2511.11793):

Stage 1: SFT (Supervised Fine-Tuning)
Stage 2: DPO (Direct Preference Optimization)
Stage 3: RL/GRPO (Reinforcement Learning with Grammar Rewards)

Our training script design followed the MiroThinker paper's architecture, including:

Higher LoRA rank (r=32, alpha=64) as recommended for multi-stage training stability
Full target modules (q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj) for comprehensive adaptation

However, this model uses only SFT because our experiments with preference optimization showed a fundamental trade-off:

Why DPO/SimPO Failed for Our Use Case

Model	CoLA MCC	GEC F1	Generation	Overall	Status
V6 SFT (Baseline)	0.624	0.191	3.29	0.516	Reference
V8 (DPO)	0.583	0.063	3.63	0.473	-8% overall
V9 (SimPO)	0.567	0.073	3.72	0.479	-7% overall

Key findings:

DPO improved generation quality (+10%) but destroyed GEC accuracy (-67%)
SimPO achieved best generation (3.72) but still regressed accuracy significantly
This confirms the "alignment tax" documented in 2025 research: 76% of preference optimization causes regression on specific tasks

For grammar teaching, accuracy is more important than fluency, so we stayed with pure SFT. The V4 dataset composition (25% CoLA-style judgment examples) proved more effective than preference optimization for our metrics.

SFT Training Configuration

Configuration based on MiroThinker recommendations for multi-stage training:

Base Model: Qwen/Qwen3-4B
LoRA Configuration:
  - Rank (r): 32
  - Alpha: 64
  - Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
  - Dropout: 0

Training Configuration:
  - Epochs: 2
  - Learning Rate: 2e-4 (linear decay)
  - Batch Size: 2 (effective: 8 with gradient accumulation)
  - Warmup: 10%
  - Precision: BF16
  - Optimizer: AdamW 8-bit

The SFT stage trains on ~9,000 curated examples covering grammar judgment, error correction, and teaching explanations.

Deployment Pipeline

After SFT training, the model goes through:

1. PEFT Merge

LoRA adapters are merged into the base model:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B")
model = PeftModel.from_pretrained(base_model, "lora_adapters/")
model = model.merge_and_unload()
model.save_pretrained("merged_model/", safe_serialization=True)

2. GGUF Quantization

For efficient local inference:

python convert_hf_to_gguf.py merged_model/ --outtype bf16 --outfile model-bf16.gguf
llama-quantize model-bf16.gguf model-Q4_K_M.gguf Q4_K_M

The Q4_K_M quantization reduces model size from ~8GB to 2.5GB while maintaining high quality.

Technical Specifications

Framework: Unsloth + Transformers + TRL + PEFT
Hardware: NVIDIA RTX 4090 (24GB VRAM)
Training Time: ~45 minutes for 2 epochs
Quantization: GGUF Q4_K_M (2.5GB)

Citation

If you use this model, please cite:

@misc{qwen3-4b-german-teacher-2025,
  author = {Jaigouk Kim},
  title = {Qwen3-4B German Teacher: A Finetuned Model for German Grammar Teaching},
  year = {2025},
  publisher = {HuggingFace},
  url = {https://huggingface.co/jaigouk/qwen3-4b-german-teacher}
}