Instructions to use viettelsecurity-ai/security-llama3.2-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use viettelsecurity-ai/security-llama3.2-3b with Transformers:

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

pipe = pipeline("text-generation", model="viettelsecurity-ai/security-llama3.2-3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("viettelsecurity-ai/security-llama3.2-3b")
model = AutoModelForCausalLM.from_pretrained("viettelsecurity-ai/security-llama3.2-3b", 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 viettelsecurity-ai/security-llama3.2-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "viettelsecurity-ai/security-llama3.2-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "viettelsecurity-ai/security-llama3.2-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/viettelsecurity-ai/security-llama3.2-3b

SGLang

How to use viettelsecurity-ai/security-llama3.2-3b 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 "viettelsecurity-ai/security-llama3.2-3b" \
    --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": "viettelsecurity-ai/security-llama3.2-3b",
		"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 "viettelsecurity-ai/security-llama3.2-3b" \
        --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": "viettelsecurity-ai/security-llama3.2-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use viettelsecurity-ai/security-llama3.2-3b with Docker Model Runner:
```
docker model run hf.co/viettelsecurity-ai/security-llama3.2-3b
```

hoangph3 commited on Mar 11, 2025

Commit

83e784a

verified ·

1 Parent(s): a33cd2c

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -101

README.md CHANGED Viewed

@@ -14,107 +14,6 @@ tags:
 - trl
 - grpo
-model-index:
-  - name: security-llama3.2-3b
-    results:
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: IFEval (0-Shot)
-          type: HuggingFaceH4/ifeval
-          args:
-            num_few_shot: 0
-        metrics:
-          - type: inst_level_strict_acc and prompt_level_strict_acc
-            value: 34.08
-            name: strict accuracy
-        source:
-          url: >-
-            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=viettelsecurity-ai/security-llama3.2-3b
-          name: Open LLM Leaderboard
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: BBH (3-Shot)
-          type: BBH
-          args:
-            num_few_shot: 3
-        metrics:
-          - type: acc_norm
-            value: 10.1
-            name: normalized accuracy
-        source:
-          url: >-
-            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=viettelsecurity-ai/security-llama3.2-3b
-          name: Open LLM Leaderboard
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: MATH Lvl 5 (4-Shot)
-          type: hendrycks/competition_math
-          args:
-            num_few_shot: 4
-        metrics:
-          - type: exact_match
-            value: 0.63
-            name: exact match
-        source:
-          url: >-
-            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=viettelsecurity-ai/security-llama3.2-3b
-          name: Open LLM Leaderboard
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: GPQA (0-shot)
-          type: Idavidrein/gpqa
-          args:
-            num_few_shot: 0
-        metrics:
-          - type: acc_norm
-            value: 0.12
-            name: acc_norm
-        source:
-          url: >-
-            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=viettelsecurity-ai/security-llama3.2-3b
-          name: Open LLM Leaderboard
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: MuSR (0-shot)
-          type: TAUR-Lab/MuSR
-          args:
-            num_few_shot: 0
-        metrics:
-          - type: acc_norm
-            value: 1.2
-            name: acc_norm
-        source:
-          url: >-
-            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=viettelsecurity-ai/security-llama3.2-3b
-          name: Open LLM Leaderboard
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: MMLU-PRO (5-shot)
-          type: TIGER-Lab/MMLU-Pro
-          config: main
-          split: test
-          args:
-            num_few_shot: 5
-        metrics:
-          - type: acc
-            value: 4.93
-            name: accuracy
-        source:
-          url: >-
-            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=viettelsecurity-ai/security-llama3.2-3b
-          name: Open LLM Leaderboard
 ---
 ## Model Overview

 - trl
 - grpo
 ---
 ## Model Overview