Instructions to use pankajmathur/orca_mini_v3_13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajmathur/orca_mini_v3_13b with Transformers:

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

pipe = pipeline("text-generation", model="pankajmathur/orca_mini_v3_13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pankajmathur/orca_mini_v3_13b")
model = AutoModelForCausalLM.from_pretrained("pankajmathur/orca_mini_v3_13b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pankajmathur/orca_mini_v3_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_v3_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_v3_13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pankajmathur/orca_mini_v3_13b

SGLang

How to use pankajmathur/orca_mini_v3_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_v3_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_v3_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_v3_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_v3_13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pankajmathur/orca_mini_v3_13b with Docker Model Runner:
```
docker model run hf.co/pankajmathur/orca_mini_v3_13b
```

Template for chat-ui

by thibautrey - opened Aug 11, 2023

Discussion

thibautrey

Aug 11, 2023

•

edited Aug 11, 2023

Could anyone provide a template for usage with chat-ui ? Like this one below ?

{
    "endpoints": [{"url": "CUSTOM_ENDPOINT"}]
    "name": "psmathur/orca_mini_v3_13b",
    "datasetName": "A Llama2-13b model trained on Orca Style datasets.",
    "description": "A Llama2-13b model trained on Orca Style datasets."
    "websiteUrl": "https://huggingface.co/psmathur/orca_mini_v3_13b",
    "userMessageToken": "### User:",
    "assistantMessageToken": "### Assistant:",
    "messageEndToken": "</s>",
    "preprompt": "\n-----\n",
    "promptExamples": [
      {
        "title": "Assist in a task",
        "prompt": "How do I make a delicious lemon cheesecake?"
      }
    ],
    "parameters": {
      "temperature": 0.2,
      "top_p": 0.95,
      "repetition_penalty": 1.2,
      "top_k": 0,
      "truncate": 1000,
      "max_new_tokens": 4096,
      "stop": ["<|endoftext|>","</s>", ">>"]
    }

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment