Instructions to use Secbone/llama-2-13B-instructed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Secbone/llama-2-13B-instructed with Transformers:

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

pipe = pipeline("text-generation", model="Secbone/llama-2-13B-instructed")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Secbone/llama-2-13B-instructed")
model = AutoModelForCausalLM.from_pretrained("Secbone/llama-2-13B-instructed", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Secbone/llama-2-13B-instructed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Secbone/llama-2-13B-instructed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Secbone/llama-2-13B-instructed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Secbone/llama-2-13B-instructed

SGLang

How to use Secbone/llama-2-13B-instructed 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 "Secbone/llama-2-13B-instructed" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Secbone/llama-2-13B-instructed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Secbone/llama-2-13B-instructed" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Secbone/llama-2-13B-instructed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Secbone/llama-2-13B-instructed with Docker Model Runner:
```
docker model run hf.co/Secbone/llama-2-13B-instructed
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LlaMA 2 13B instruction finetuned

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	47.84
ARC (25-shot)	59.39
HellaSwag (10-shot)	83.88
MMLU (5-shot)	55.57
TruthfulQA (0-shot)	46.89
Winogrande (5-shot)	74.03
GSM8K (5-shot)	8.04
DROP (3-shot)	7.06

Downloads last month: 51

Model tree for Secbone/llama-2-13B-instructed

Quantizations

1 model

Secbone
/

llama-2-13B-instructed

LlaMA 2 13B instruction finetuned

Open LLM Leaderboard Evaluation Results

Model tree for Secbone/llama-2-13B-instructed

Spaces using Secbone/llama-2-13B-instructed 9