Instructions to use pankajmathur/orca_mini_v2_13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajmathur/orca_mini_v2_13b with Transformers:

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

pipe = pipeline("text-generation", model="pankajmathur/orca_mini_v2_13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pankajmathur/orca_mini_v2_13b")
model = AutoModelForCausalLM.from_pretrained("pankajmathur/orca_mini_v2_13b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pankajmathur/orca_mini_v2_13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pankajmathur/orca_mini_v2_13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pankajmathur/orca_mini_v2_13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pankajmathur/orca_mini_v2_13b

SGLang

How to use pankajmathur/orca_mini_v2_13b 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 "pankajmathur/orca_mini_v2_13b" \
    --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": "pankajmathur/orca_mini_v2_13b",
		"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 "pankajmathur/orca_mini_v2_13b" \
        --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": "pankajmathur/orca_mini_v2_13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pankajmathur/orca_mini_v2_13b with Docker Model Runner:
```
docker model run hf.co/pankajmathur/orca_mini_v2_13b
```

orca_mini_v2_13b

Commit History

Adding `safetensors` variant of this model (#3)

212bb14
verified

pankajmathur

SFconvertbot commited on Jun 12, 2025

Update README.md

a832d67
verified

pankajmathur commited on Dec 29, 2024

Update README.md

eecc9a6
verified

pankajmathur commited on Jul 7, 2024

Adding Evaluation Results (#2)

60d75cc
verified

pankajmathur

leaderboard-pr-bot commited on Mar 4, 2024