Instructions to use singhabhishekkk/apprentice-gemma4-e4b-lora-document-types with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use singhabhishekkk/apprentice-gemma4-e4b-lora-document-types with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-e4b-it-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "singhabhishekkk/apprentice-gemma4-e4b-lora-document-types")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use singhabhishekkk/apprentice-gemma4-e4b-lora-document-types with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M

Use Docker

docker model run hf.co/singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use singhabhishekkk/apprentice-gemma4-e4b-lora-document-types with Ollama:
```
ollama run hf.co/singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M
```
Unsloth Desktop

How to use singhabhishekkk/apprentice-gemma4-e4b-lora-document-types with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use singhabhishekkk/apprentice-gemma4-e4b-lora-document-types with Docker Model Runner:
```
docker model run hf.co/singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M
```

Lemonade

How to use singhabhishekkk/apprentice-gemma4-e4b-lora-document-types with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M

Run and chat with the model

lemonade run user.apprentice-gemma4-e4b-lora-document-types-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use singhabhishekkk/apprentice-gemma4-e4b-lora-document-types with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singhabhishekkk/apprentice-gemma4-e4b-lora-document-types: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 singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use singhabhishekkk/apprentice-gemma4-e4b-lora-document-types with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M

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 "singhabhishekkk/apprentice-gemma4-e4b-lora-document-types:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Apprentice Gemma 4 E4B LoRA (document type classification)

LoRA adapter fine-tuned on 140 golden examples from a corrected Tobacco3482 OCR-text dataset to classify one document type from: ADVE, Email, Form, Letter, Memo, News, Note, Report, Resume, Scientific.

The input prompt is the verbatim shipped document-type prompt from icereed/paperless-gpt, filled with English, the allowed type list, an empty title, and OCR text capped at about 4,000 characters.

Results (60 held-out rows, exact match)

Model	Score
gpt-5.4-mini, plain paperless-gpt prompt	78.33
gpt-5.4-mini, GEPA-optimized prompt	81.67
Gemma 4 E4B, no fine-tune	63.33
Gemma 4 E4B, fine-tuned on 140 examples (this adapter)	86.67

Same 60 held-out rows, same seed, same split for every row. The fine-tuned model scores +8.34 over the shipped prompt and +5.00 over the GEPA-optimized teacher. Gemma run 2026-07-12; gpt-5.4-mini runs 2026-07-10. Full method, data prep, notebooks and caveats: apprentice-benchmark, document type task.

Training

LoRA r=16, alpha 16, 3 epochs, lr 2e-4, batch 2 x grad-accum 4, Unsloth 4-bit, Colab GPU. Train/eval split: seed 42, 140/60 from 200 sampled rows, identical split across every model this task is fine-tuned on.

Usage

Load with PEFT on top of google/gemma-4-E4B-it, or serve locally with an adapter-capable runtime. Caveat: evaluated on 60 rows for one field only. Re-validate on your paperless-ngx document types before production use.

Downloads last month: 35

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for singhabhishekkk/apprentice-gemma4-e4b-lora-document-types

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Adapter

(436)

this model

singhabhishekkk
/

apprentice-gemma4-e4b-lora-document-types

Apprentice Gemma 4 E4B LoRA (document type classification)

Results (60 held-out rows, exact match)

Training

Usage

Model tree for singhabhishekkk/apprentice-gemma4-e4b-lora-document-types

Dataset used to train singhabhishekkk/apprentice-gemma4-e4b-lora-document-types