Instructions to use pankajmathur/orca_mini_v3_70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajmathur/orca_mini_v3_70b with Transformers:

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

pipe = pipeline("text-generation", model="pankajmathur/orca_mini_v3_70b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pankajmathur/orca_mini_v3_70b")
model = AutoModelForCausalLM.from_pretrained("pankajmathur/orca_mini_v3_70b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pankajmathur/orca_mini_v3_70b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pankajmathur/orca_mini_v3_70b"
# 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_v3_70b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pankajmathur/orca_mini_v3_70b

SGLang

How to use pankajmathur/orca_mini_v3_70b 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_v3_70b" \
    --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_v3_70b",
		"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_v3_70b" \
        --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_v3_70b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pankajmathur/orca_mini_v3_70b with Docker Model Runner:
```
docker model run hf.co/pankajmathur/orca_mini_v3_70b
```

orca_mini_v3_70b / README.md

Commit History

Adding Evaluation Results

3fe76db
verified

leaderboard-pr-bot commited on Jul 18, 2024

Update README.md

ca1181a
verified

pankajmathur commited on Jul 7, 2024

Adding Evaluation Results (#7)

e8e856d
verified

pankajmathur

leaderboard-pr-bot commited on Mar 4, 2024

Adding Evaluation Results (#6)

01e7875

pankajmathur

leaderboard-pr-bot commited on Nov 18, 2023

Update README.md

5f990de

pankajmathur commited on Nov 9, 2023

Update README.md

5f3d251

pankajmathur commited on Nov 9, 2023

Update README.md

5267da9

Pankaj Mathur commited on Aug 25, 2023

Update README.md

f1458f9

Pankaj Mathur commited on Aug 18, 2023

Update README.md

c1d4f99

Pankaj Mathur commited on Aug 16, 2023

Update README.md

15d6291

Pankaj Mathur commited on Aug 15, 2023

Create README.md

d0afcea

Pankaj Mathur commited on Aug 15, 2023

Commit History

Adding Evaluation Results 3fe76db verified

Update README.md ca1181a verified

Adding Evaluation Results (#7) e8e856d verified

Adding Evaluation Results (#6) 01e7875

Update README.md 5f990de

Update README.md 5f3d251

Update README.md 5267da9

Update README.md f1458f9

Update README.md c1d4f99

Update README.md 15d6291

Create README.md d0afcea