Instructions to use alwaysgood/Gemma4_E2B_ADS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alwaysgood/Gemma4_E2B_ADS with Transformers:

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("alwaysgood/Gemma4_E2B_ADS")
model = AutoModelForMultimodalLM.from_pretrained("alwaysgood/Gemma4_E2B_ADS", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use alwaysgood/Gemma4_E2B_ADS 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 alwaysgood/Gemma4_E2B_ADS:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alwaysgood/Gemma4_E2B_ADS:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf alwaysgood/Gemma4_E2B_ADS:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alwaysgood/Gemma4_E2B_ADS: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 alwaysgood/Gemma4_E2B_ADS:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf alwaysgood/Gemma4_E2B_ADS: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 alwaysgood/Gemma4_E2B_ADS:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alwaysgood/Gemma4_E2B_ADS:Q4_K_M

Use Docker

docker model run hf.co/alwaysgood/Gemma4_E2B_ADS:Q4_K_M

LM Studio
Jan
Ollama
How to use alwaysgood/Gemma4_E2B_ADS with Ollama:
```
ollama run hf.co/alwaysgood/Gemma4_E2B_ADS:Q4_K_M
```
Unsloth Desktop

How to use alwaysgood/Gemma4_E2B_ADS with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alwaysgood/Gemma4_E2B_ADS: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": "alwaysgood/Gemma4_E2B_ADS:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use alwaysgood/Gemma4_E2B_ADS with Docker Model Runner:
```
docker model run hf.co/alwaysgood/Gemma4_E2B_ADS:Q4_K_M
```

Lemonade

How to use alwaysgood/Gemma4_E2B_ADS with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alwaysgood/Gemma4_E2B_ADS:Q4_K_M

Run and chat with the model

lemonade run user.Gemma4_E2B_ADS-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use alwaysgood/Gemma4_E2B_ADS with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alwaysgood/Gemma4_E2B_ADS: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 alwaysgood/Gemma4_E2B_ADS:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use alwaysgood/Gemma4_E2B_ADS with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alwaysgood/Gemma4_E2B_ADS: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 "alwaysgood/Gemma4_E2B_ADS: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"

alwaysgood commited on 9 days ago

Commit

cb70332

verified ·

1 Parent(s): 6383c9c

Add LM Studio Q4_K_M GGUF export

Browse files

Files changed (5) hide show

.gitattributes +2 -0
Gemma4_E2B_ADS-Q4_K_M.gguf +3 -0
README.md +94 -0
SHA256SUMS +2 -0
mmproj-Gemma4_E2B_ADS-BF16.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Gemma4_E2B_ADS-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-Gemma4_E2B_ADS-BF16.gguf filter=lfs diff=lfs merge=lfs -text

Gemma4_E2B_ADS-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:91d0f1f116877445c0e9db71eb31f0b6abf073089ee70735562daeeb818be504
+size 3427878176

README.md ADDED Viewed

	@@ -0,0 +1,94 @@

+---
+license: apache-2.0
+base_model:
+  - google/gemma-4-E2B-it
+base_model_relation: finetune
+datasets:
+  - alwaysgood/financial-english-source-corpus
+  - alwaysgood/financial-english-source-corpus-gemma4-e2b-1280
+language:
+  - en
+  - ko
+library_name: transformers
+pipeline_tag: any-to-any
+tags:
+  - translation
+  - financial-translation
+  - english-to-korean
+  - conversational
+  - multimodal
+  - safetensors
+  - gguf
+  - llama-cpp
+  - lm-studio
+  - q4_k_m
+---
+# Gemma4_E2B_ADS
+Gemma4_E2B_ADS is a full fine-tune of
+[`google/gemma-4-E2B-it`](https://huggingface.co/google/gemma-4-E2B-it) for
+English-to-Korean financial translation. It was trained with the DQS
+low-QE curriculum using seed 42.
+This repository contains both the original Transformers checkpoint and one
+LM Studio/llama.cpp export:
+- `model.safetensors`: original BF16 fine-tuned checkpoint
+- `Gemma4_E2B_ADS-Q4_K_M.gguf`: the only quantized main-model variant
+- `mmproj-Gemma4_E2B_ADS-BF16.gguf`: multimodal encoder/projector companion
+The BF16 `mmproj` is not an additional LLM quantization variant. It is kept at
+BF16 for multimodal compatibility and quality.
+## LM Studio
+Use the latest LM Studio runtime and download the Q4_K_M variant:
+```bash
+lms get https://huggingface.co/alwaysgood/Gemma4_E2B_ADS@Q4_K_M
+```
+The matching `mmproj` file enables image input. Direct llama.cpp multimodal
+testing with this checkpoint requires `--jinja`. Gemma 4 audio support may vary
+by runtime and is not guaranteed by this model card. For translation, disable
+thinking and ask for translation-only output, for example:
+```text
+Translate the following English financial text into Korean. Return only the translation.
+<source text>
+```
+## Training and provenance
+- Tuning: full-parameter supervised fine-tuning
+- Seed: 42
+- Selection: low quality-estimation score first (`qe_selection_order=low`)
+- Base model thinking during training/evaluation: disabled
+- Vision/audio layers: not trained; the base model's multimodal components were preserved
+- Run artifacts: [`gemma4_e2b_it_full_lowqe_seed42`](https://huggingface.co/datasets/alwaysgood/dqs-runs/tree/fa8166a883d96460cc285b46d66b74a074b4b8d4/gemma4_e2b_it_full_lowqe_seed42)
+- Source revision: `fa8166a883d96460cc285b46d66b74a074b4b8d4`
+## Evaluation
+The following scores are from the original BF16 final checkpoint on the
+500-row held-out test set. They are not claimed as a separate Q4_K_M evaluation.
+| Metric | Score |
+|---|---:|
+| BLEU | 30.7621 |
+| chrF | 49.3295 |
+| COMET (`wmt22-comet-da`) | 0.8968 |
+| COMETKiwi (`wmt22-cometkiwi-da`) | 0.8630 |
+| XCOMET-XXL | 0.8746 |
+| MetricX-24 Hybrid XXL (lower is better) | 3.4078 |
+Full evaluation records and configuration are available in the linked run.
+## License and data note
+The model weights follow the Apache-2.0 license of the base model. The training
+corpus aggregates sources with mixed upstream terms; the dataset card is marked
+`license: other`. Users are responsible for reviewing the source-specific terms
+described in [`alwaysgood/financial-english-source-corpus`](https://huggingface.co/datasets/alwaysgood/financial-english-source-corpus).

SHA256SUMS ADDED Viewed

	@@ -0,0 +1,2 @@


1	+ 91d0f1f116877445c0e9db71eb31f0b6abf073089ee70735562daeeb818be504 Gemma4_E2B_ADS-Q4_K_M.gguf
2	+ 9e10f628678c2271e875b16211c262b4af319ad8b8491588ed4a9753a93c1acd mmproj-Gemma4_E2B_ADS-BF16.gguf

mmproj-Gemma4_E2B_ADS-BF16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e10f628678c2271e875b16211c262b4af319ad8b8491588ed4a9753a93c1acd
+size 986833248