Instructions to use naazimsnh02/gemma-4-e4b-opus-reasoning-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use naazimsnh02/gemma-4-e4b-opus-reasoning-v2 with Transformers:

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

pipe = pipeline("text-generation", model="naazimsnh02/gemma-4-e4b-opus-reasoning-v2")
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("naazimsnh02/gemma-4-e4b-opus-reasoning-v2")
model = AutoModelForMultimodalLM.from_pretrained("naazimsnh02/gemma-4-e4b-opus-reasoning-v2")
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

vLLM

How to use naazimsnh02/gemma-4-e4b-opus-reasoning-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "naazimsnh02/gemma-4-e4b-opus-reasoning-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "naazimsnh02/gemma-4-e4b-opus-reasoning-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/naazimsnh02/gemma-4-e4b-opus-reasoning-v2

SGLang

How to use naazimsnh02/gemma-4-e4b-opus-reasoning-v2 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 "naazimsnh02/gemma-4-e4b-opus-reasoning-v2" \
    --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": "naazimsnh02/gemma-4-e4b-opus-reasoning-v2",
		"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 "naazimsnh02/gemma-4-e4b-opus-reasoning-v2" \
        --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": "naazimsnh02/gemma-4-e4b-opus-reasoning-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use naazimsnh02/gemma-4-e4b-opus-reasoning-v2 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 naazimsnh02/gemma-4-e4b-opus-reasoning-v2 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 naazimsnh02/gemma-4-e4b-opus-reasoning-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for naazimsnh02/gemma-4-e4b-opus-reasoning-v2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="naazimsnh02/gemma-4-e4b-opus-reasoning-v2",
    max_seq_length=2048,
)

Docker Model Runner
How to use naazimsnh02/gemma-4-e4b-opus-reasoning-v2 with Docker Model Runner:
```
docker model run hf.co/naazimsnh02/gemma-4-e4b-opus-reasoning-v2
```

naazimsnh02 commited on Apr 5

Commit

1df3404

verified ·

1 Parent(s): 8271908

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -17

README.md CHANGED Viewed

@@ -29,8 +29,6 @@ model-index:
 A reasoning-enhanced fine-tune of [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it), distilled from Claude Opus 4.6 reasoning traces with supplementary math Chain-of-Thought data.
-The model produces structured `<think>...</think>` reasoning blocks before delivering a final answer, encouraging step-by-step problem solving across general reasoning, coding, and mathematics tasks.
 ## Model Details
 | | |
@@ -91,7 +89,7 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 tokenizer = AutoTokenizer.from_pretrained("naazimsnh02/gemma-4-e4b-opus-reasoning-v2")
-messages = [{"role": "user", "content": "What is 25 * 37? Think step by step."}]
 inputs = tokenizer.apply_chat_template(
     messages,
     add_generation_prompt=True,
@@ -104,20 +102,6 @@ output = model.generate(**inputs, max_new_tokens=1024, temperature=1.0, top_p=0.
 print(tokenizer.decode(output[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
 ```
-### Expected Output Format
-```
-<think>
-Let me work through this step by step.
-25 * 37
-= 25 * (40 - 3)
-= 1000 - 75
-= 925
-</think>
-The answer is **925**.
-```
 ## Limitations & Disclaimers
 - **This is a reasoning-focused model, not a benchmark-optimized release.** It has not been evaluated on standard benchmarks (MMLU, GSM8K, HumanEval, etc.). Performance on such benchmarks is unknown and may differ from the base model.

 A reasoning-enhanced fine-tune of [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it), distilled from Claude Opus 4.6 reasoning traces with supplementary math Chain-of-Thought data.
 ## Model Details
 | | |
 )
 tokenizer = AutoTokenizer.from_pretrained("naazimsnh02/gemma-4-e4b-opus-reasoning-v2")
+messages = [{"role": "user", "content": "A train travels 60 km/h. How long does it take to cover 255 km?"}]
 inputs = tokenizer.apply_chat_template(
     messages,
     add_generation_prompt=True,
 print(tokenizer.decode(output[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
 ```
 ## Limitations & Disclaimers
 - **This is a reasoning-focused model, not a benchmark-optimized release.** It has not been evaluated on standard benchmarks (MMLU, GSM8K, HumanEval, etc.). Performance on such benchmarks is unknown and may differ from the base model.