Instructions to use Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep with Transformers:

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

pipe = pipeline("text-generation", model="Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep")
model = AutoModelForCausalLM.from_pretrained("Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep

SGLang

How to use Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep 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 "Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep" \
    --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": "Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep",
		"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 "Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep" \
        --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": "Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep with Docker Model Runner:
```
docker model run hf.co/Heoni/gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep
```

gemma_3_4b_it_ko_r1_3.2.4_20250724_4ep / config.json

yangdonghun3

Upload Gemma3ForCausalLM

18b475a verified about 1 year ago

Raw

History Blame Contribute Delete

928 Bytes

	{
	"architectures": [
	"Gemma3ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_logit_softcapping": null,
	"bos_token_id": 2,
	"cache_implementation": "hybrid",
	"eos_token_id": 1,
	"final_logit_softcapping": null,
	"head_dim": 256,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 2560,
	"initializer_range": 0.02,
	"intermediate_size": 10240,
	"max_position_embeddings": 131072,
	"model_type": "gemma3_text",
	"num_attention_heads": 8,
	"num_hidden_layers": 34,
	"num_key_value_heads": 4,
	"pad_token_id": 0,
	"query_pre_attn_scalar": 256,
	"rms_norm_eps": 1e-06,
	"rope_local_base_freq": 10000.0,
	"rope_scaling": {
	"factor": 8.0,
	"rope_type": "linear"
	},
	"rope_theta": 1000000.0,
	"sliding_window": 1024,
	"sliding_window_pattern": 6,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.51.3",
	"use_cache": true,
	"vocab_size": 262208
	}