Instructions to use helenk/gemma-4-E4B-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use helenk/gemma-4-E4B-finetune with Transformers:

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

pipe = pipeline("text-generation", model="helenk/gemma-4-E4B-finetune")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("helenk/gemma-4-E4B-finetune")
model = AutoModelForMultimodalLM.from_pretrained("helenk/gemma-4-E4B-finetune")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use helenk/gemma-4-E4B-finetune with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use helenk/gemma-4-E4B-finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "helenk/gemma-4-E4B-finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "helenk/gemma-4-E4B-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/helenk/gemma-4-E4B-finetune

SGLang

How to use helenk/gemma-4-E4B-finetune 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 "helenk/gemma-4-E4B-finetune" \
    --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": "helenk/gemma-4-E4B-finetune",
		"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 "helenk/gemma-4-E4B-finetune" \
        --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": "helenk/gemma-4-E4B-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use helenk/gemma-4-E4B-finetune 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 helenk/gemma-4-E4B-finetune 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 helenk/gemma-4-E4B-finetune to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for helenk/gemma-4-E4B-finetune to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="helenk/gemma-4-E4B-finetune",
    max_seq_length=2048,
)

Docker Model Runner
How to use helenk/gemma-4-E4B-finetune with Docker Model Runner:
```
docker model run hf.co/helenk/gemma-4-E4B-finetune
```

OfflineAid — Gemma 4 E4B fine-tune (merged fp16 safetensors)

Stage-1 fine-tune of unsloth/gemma-4-E4B-it for the OfflineAid Mac-side pack-builder agent — an offline AI assistant for Australian consumer-safety scenarios (anti-scam, disaster, travel) targeting the Kaggle Gemma 4 Good Hackathon.

This repo contains the fully merged fp16 safetensors (4 shards, ~16 GB) produced by peft.PeftModel.merge_and_unload() from the LoRA adapter at helenk/gemma-4-E4B-lora. For the Q4_K_M GGUF quantization that ships with Ollama, see helenk/gemma-4-E4B-finetune-GGUF.

Tier A held-out eval (vs stock + RAG)

Held-out: 111 rows stratified per-language (37 EN + 37 ZH + 37 AR) from the 1,113-row helenkwok/offlineaid corpus, seed=3407. Q4_K_M-quantized version evaluated against stock gemma4-stock (also Q4_K_M) via Ollama. Greedy decoding, explicit "Answer in {language}" directive.

Language	Metric	stock + RAG	ft + RAG	Δ
EN	ROUGE-L F1	0.688	0.699	+0.011
EN	Format-OK %	91.9%	94.6%	+2.7 pp
ZH	ROUGE-L F1	0.229	0.227	−0.002
ZH	Format-OK %	45.9%	62.2%	+16.3 pp
AR	ROUGE-L F1	0.085	0.139	+63%
AR	Format-OK %	21.6%	54.1%	+32.4 pp (2.5×)
all	ROUGE-L F1	0.334	0.355	+0.021
all	Format-OK %	53.2%	70.3%	+17.0 pp

Format-OK = pred is non-empty AND contains at least one character in the expected script (CJK for ZH, Arabic for AR, ASCII for EN). The honest multilingual signal — ROUGE-L is lexically blind to two valid translations of the same English source.

Training

Method: Unsloth LoRA on Kaggle T4 (1× T4, ~7 min)
Adapter source: helenk/gemma-4-E4B-lora
Base: unsloth/gemma-4-E4B-it
LoRA config: r=16, α=16, dropout=0, target = q,k,v,o,gate,up,down_proj, vision layers off
Chat template: gemma-4-thinking
Loss: train_on_responses_only (mask user + evidence turn, train only on answer tokens)
Data: helenkwok/offlineaid v3 — 1,002-row train split (90/10 stratified per-language EN/ZH/AR from 1,113-row total, seed=3407). Each row is {instruction, input (= verbatim evidence_quote from .gov.au source), output (grounded answer in target language), language}.
Hyperparams: 2 epochs, batch 8 (per_device 2 × grad_accum 4), lr 2e-5, warmup 5, fp16, weight decay 0.01, seed 3407
Notebook: scripts/render_finetune_variant.py renders one canonical notebook to E2B and E4B variants; canonical at notebooks/_canonical-finetune.ipynb.

Merge recipe

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-E4B-it", torch_dtype="float16", device_map="cpu")
# Unsloth wraps Linear layers in Gemma4ClippableLinear — strip before peft injection
# (see scripts/merge_e4b_lora.py for the unwrap helper)
model = PeftModel.from_pretrained(base, "helenk/gemma-4-E4B-lora").merge_and_unload()
model.save_pretrained("gemma-4-E4B-offlineaid-merged", safe_serialization=True, max_shard_size="5GB")
AutoTokenizer.from_pretrained("helenk/gemma-4-E4B-lora").save_pretrained("gemma-4-E4B-offlineaid-merged")

Full script: scripts/merge_e4b_lora.py.

Intended use

Stage 3 of the OfflineAid pipeline — Mac-side pack-builder agent loop (Ollama via pydantic-ai). Pixel 7 production deployment uses the stock gemma-4-E2B-it.litertlm plus retrieval, not this fine-tune; see the project writeup for the architectural rationale.