Instructions to use AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k with Transformers:

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

pipe = pipeline("image-text-to-text", model="AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k")
model = AutoModelForImageTextToText.from_pretrained("AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k")
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]:]))

llama-cpp-python

How to use AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k",
	filename="model-q4.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k
# Run inference directly in the terminal:
llama-cli -hf AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k
# Run inference directly in the terminal:
llama-cli -hf AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k

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 AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k
# Run inference directly in the terminal:
./llama-cli -hf AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k

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 AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k

Use Docker

docker model run hf.co/AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k

LM Studio
Jan

vLLM

How to use AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k

SGLang

How to use AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k 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 "AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k" \
    --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": "AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k" \
        --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": "AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k with Ollama:
```
ollama run hf.co/AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k
```

Unsloth Studio new

How to use AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k 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 AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k 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 AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k to start chatting

Docker Model Runner
How to use AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k with Docker Model Runner:
```
docker model run hf.co/AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k
```

Lemonade

How to use AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AlexHung29629/gemma4-e4b-sft-4gpu-fullft-32k

Run and chat with the model

lemonade run user.gemma4-e4b-sft-4gpu-fullft-32k-{{QUANT_TAG}}

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

See axolotl config

axolotl version: 0.16.0.dev0

# config-4gpu-fullft-e4b-32k.yml
base_model: /models/gemma-4-e4b-it

embeddings_skip_upcast: true
trust_remote_code: true
chat_template: gemma
unfrozen_parameters:
  - model.language_model.layers.(2|3|4)[\d].(_checkpoint_wrapped_module.)?(mlp).(up|down|gate)_proj
# ====================== 多 GPU 設定 (FSDP) ======================
fsdp_version: 2
fsdp_config:
  offload_params: false
  state_dict_type: FULL_STATE_DICT
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: Gemma4TextDecoderLayer
# ====================== Liger Kernel ======================
plugins:
  - axolotl.integrations.liger.LigerPlugin

torch_compile: false
liger_layer_norm: false
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_rms_norm_gated: true
sdp_attention: true

# ====================== 資料集 ======================
datasets:
  - path: /notebook/train_segments.jsonl
    type: input_output

dataset_processes: 4
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

# ====================== 關鍵：長上下文 32768 ======================
sequence_len: 16384
micro_batch_size: 1 # 32k 必須從 1 開始，避免 OOM
gradient_accumulation_steps: 1 # effective batch size ≈ 1×4×8 = 32（推薦 DPO 值）
max_grad_norm: 1
num_epochs: 2

# 記憶體優化（32k 長上下文非常吃 activations）
gradient_checkpointing: true
activation_offloading: false # 強烈建議開啟

# 優化器
optimizer: adamw_torch
lr_scheduler: constant
learning_rate: 5e-6

# 混合精度
bf16: true
tf32: true

# 保存與紀錄
save_safetensors: true
save_strategy: epoch
saves_per_epoch: 1
logging_steps: 5 # 長上下文時 logging 頻率提高一點
output_dir: ./outputs/gemma4-e4b-sft-4gpu-fullft-32k

use_tensorboard: true
#hub_model_id: AlexHung29629/WhiteDubstepFly

outputs/gemma4-e4b-sft-4gpu-fullft-32k

This model was trained from scratch on the /notebook/train_segments.jsonl dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 4
total_eval_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 7
training_steps: 262

Training results

Framework versions

Transformers 5.5.0
Pytorch 2.10.0+cu130
Datasets 4.5.0
Tokenizers 0.22.2

Downloads last month: 13

Safetensors

Model size

9B params

Tensor type

BF16