Instructions to use Bllossom/llama-3.2-Korean-Bllossom-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bllossom/llama-3.2-Korean-Bllossom-3B with Transformers:

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

pipe = pipeline("text-generation", model="Bllossom/llama-3.2-Korean-Bllossom-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Bllossom/llama-3.2-Korean-Bllossom-3B")
model = AutoModelForMultimodalLM.from_pretrained("Bllossom/llama-3.2-Korean-Bllossom-3B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Bllossom/llama-3.2-Korean-Bllossom-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Bllossom/llama-3.2-Korean-Bllossom-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bllossom/llama-3.2-Korean-Bllossom-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Bllossom/llama-3.2-Korean-Bllossom-3B

SGLang

How to use Bllossom/llama-3.2-Korean-Bllossom-3B 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 "Bllossom/llama-3.2-Korean-Bllossom-3B" \
    --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": "Bllossom/llama-3.2-Korean-Bllossom-3B",
		"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 "Bllossom/llama-3.2-Korean-Bllossom-3B" \
        --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": "Bllossom/llama-3.2-Korean-Bllossom-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Bllossom/llama-3.2-Korean-Bllossom-3B with Docker Model Runner:
```
docker model run hf.co/Bllossom/llama-3.2-Korean-Bllossom-3B
```

add AIBOM

#15

by RiccardoDav - opened Jun 12, 2025

base: refs/heads/main

←

from: refs/pr/15

Discussion Files changed

+65

-0

Files changed (1) hide show

Bllossom_llama-3.2-Korean-Bllossom-3B.json +65 -0

Bllossom_llama-3.2-Korean-Bllossom-3B.json ADDED Viewed

	@@ -0,0 +1,65 @@

+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:fff809d2-9fce-4cd9-8d61-d4c5966240c9",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:40:59.491105+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "Bllossom/llama-3.2-Korean-Bllossom-3B-1face753-d759-513c-b283-594687978102",
+            "name": "Bllossom/llama-3.2-Korean-Bllossom-3B",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/Bllossom/llama-3.2-Korean-Bllossom-3B",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "text-generation",
+                    "architectureFamily": "llama",
+                    "modelArchitecture": "LlamaForCausalLM"
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    },
+                    {
+                        "name": "base_model",
+                        "value": "meta-llama/Meta-Llama-3.2-3B"
+                    }
+                ]
+            },
+            "authors": [
+                {
+                    "name": "Bllossom"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "name": "llama3.2"
+                    }
+                }
+            ],
+            "tags": [
+                "transformers",
+                "safetensors",
+                "llama",
+                "text-generation",
+                "conversational",
+                "en",
+                "ko",
+                "arxiv:2403.10882",
+                "arxiv:2403.11399",
+                "license:llama3.2",
+                "autotrain_compatible",
+                "text-generation-inference",
+                "endpoints_compatible",
+                "region:us"
+            ]
+        }
+    }
+}