Instructions to use rimashussain/gemma4-cubicasa-floorplan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rimashussain/gemma4-cubicasa-floorplan with Transformers:

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

pipe = pipeline("image-text-to-text", model="rimashussain/gemma4-cubicasa-floorplan")
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("rimashussain/gemma4-cubicasa-floorplan")
model = AutoModelForMultimodalLM.from_pretrained("rimashussain/gemma4-cubicasa-floorplan")
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 rimashussain/gemma4-cubicasa-floorplan with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rimashussain/gemma4-cubicasa-floorplan",
	filename="gemma-4-E4B-it.F16-mmproj.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 Settings

llama.cpp

How to use rimashussain/gemma4-cubicasa-floorplan 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 rimashussain/gemma4-cubicasa-floorplan:F16
# Run inference directly in the terminal:
llama cli -hf rimashussain/gemma4-cubicasa-floorplan:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rimashussain/gemma4-cubicasa-floorplan:F16
# Run inference directly in the terminal:
llama cli -hf rimashussain/gemma4-cubicasa-floorplan:F16

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 rimashussain/gemma4-cubicasa-floorplan:F16
# Run inference directly in the terminal:
./llama-cli -hf rimashussain/gemma4-cubicasa-floorplan:F16

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 rimashussain/gemma4-cubicasa-floorplan:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rimashussain/gemma4-cubicasa-floorplan:F16

Use Docker

docker model run hf.co/rimashussain/gemma4-cubicasa-floorplan:F16

LM Studio
Jan

vLLM

How to use rimashussain/gemma4-cubicasa-floorplan with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rimashussain/gemma4-cubicasa-floorplan"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rimashussain/gemma4-cubicasa-floorplan",
		"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/rimashussain/gemma4-cubicasa-floorplan:F16

SGLang

How to use rimashussain/gemma4-cubicasa-floorplan 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 "rimashussain/gemma4-cubicasa-floorplan" \
    --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": "rimashussain/gemma4-cubicasa-floorplan",
		"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 "rimashussain/gemma4-cubicasa-floorplan" \
        --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": "rimashussain/gemma4-cubicasa-floorplan",
		"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 rimashussain/gemma4-cubicasa-floorplan with Ollama:
```
ollama run hf.co/rimashussain/gemma4-cubicasa-floorplan:F16
```

Unsloth Studio

How to use rimashussain/gemma4-cubicasa-floorplan 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 rimashussain/gemma4-cubicasa-floorplan 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 rimashussain/gemma4-cubicasa-floorplan to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rimashussain/gemma4-cubicasa-floorplan to start chatting

How to use rimashussain/gemma4-cubicasa-floorplan with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rimashussain/gemma4-cubicasa-floorplan:F16

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": "rimashussain/gemma4-cubicasa-floorplan:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use rimashussain/gemma4-cubicasa-floorplan with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rimashussain/gemma4-cubicasa-floorplan:F16

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 rimashussain/gemma4-cubicasa-floorplan:F16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use rimashussain/gemma4-cubicasa-floorplan with Docker Model Runner:
```
docker model run hf.co/rimashussain/gemma4-cubicasa-floorplan:F16
```

Lemonade

How to use rimashussain/gemma4-cubicasa-floorplan with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rimashussain/gemma4-cubicasa-floorplan:F16

Run and chat with the model

lemonade run user.gemma4-cubicasa-floorplan-F16

List all available models

lemonade list

rimashussain commited on Apr 17

Commit

f194141

verified ·

1 Parent(s): 96e363a

Arsenal fine-tune round 1

Browse files

Files changed (2) hide show

adapter_config.json +5 -21
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -1,18 +1,8 @@
 {
-  "alora_invocation_tokens": null,
   "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": {
-    "base_model_class": "Gemma4ForConditionalGeneration",
-    "parent_library": "transformers.models.gemma4.modeling_gemma4",
-    "unsloth_fixed": true
-  },
-  "base_model_name_or_path": "google/gemma-4-E4B-it",
   "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -21,22 +11,16 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_bias": false,
-  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 16,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|q_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|linear|embedding_projection|relative_k_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|q_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|linear|embedding_projection|relative_k_proj)))",
-  "target_parameters": null,
   "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
   "use_dora": false,
-  "use_qalora": false,
   "use_rslora": false
 }

 {
   "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-4b-it",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
+  "target_modules": "model\\.language_model\\.layers\\.\\d+\\.self_attn\\.(q_proj|v_proj|k_proj|o_proj)",
   "task_type": "CAUSAL_LM",
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0663609dd1947c4941f45705ed136968babe5c8462a9cfa9fdbf32b56f3716bf
-size 165012392

 version https://git-lfs.github.com/spec/v1
+oid sha256:f1c1e44955730b5ebfb1224295d68118ff0d2bcd4df7968334227774742d8131
+size 17865944