Instructions to use harborwater/wizard-orca-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use harborwater/wizard-orca-3b with Transformers:

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

pipe = pipeline("text-generation", model="harborwater/wizard-orca-3b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("harborwater/wizard-orca-3b")
model = AutoModelForCausalLM.from_pretrained("harborwater/wizard-orca-3b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use harborwater/wizard-orca-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "harborwater/wizard-orca-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "harborwater/wizard-orca-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/harborwater/wizard-orca-3b

SGLang

How to use harborwater/wizard-orca-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 "harborwater/wizard-orca-3b" \
    --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": "harborwater/wizard-orca-3b",
		"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 "harborwater/wizard-orca-3b" \
        --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": "harborwater/wizard-orca-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use harborwater/wizard-orca-3b with Docker Model Runner:
```
docker model run hf.co/harborwater/wizard-orca-3b
```

Conversion of Your Models to .GGUF Format as "openLlama" models

by maddes8cht - opened Nov 26, 2023

Discussion

maddes8cht

Nov 26, 2023

Hello Harborwater,

first and foremost, thank you for your models!

I wanted to inform you that I've taken the initiative to convert your models to .GGUF for use in Llama.cpp software. This particular model can be found here, and the entire collection, including other OpenLlama conversions, is available here.

So, as there is only ONE 3b version of Llama, and i was able to convert this thing here with a Llama converter script, this Model too must be an OpenLlama descendant, isn't it?
While I understand that it's acceptable not to include OpenLlama in the model name (as you did in all your other Models), I believe adding a note in the model card about its OpenLlama descendant status would be beneficial for clarity.

I refer to this model as an OpenLlama descendant, and I would like to have a confirmation if that is correct?

If you find it fitting, linking back to the converted models on your README.md files could create a mutually beneficial connection.

Thank you for your time and consideration.

Best regards,
maddes8cht

harborwater

Owner Nov 29, 2023

Greetings maddes8cht!

thank you for taking the time to reach out me.

This model is indeed a Open llama descendant , at the time of uploading this model I forgot to add that in the model name. I will add it to the model card as soon as I can for better clarity.

as for the .GGUF models, I will also add those links to all the model cards this upcoming weekend.

I also want to thank you for taking the initiative to convert my models to .GGUF format as I have no experience converting models to other formats.

If you have anymore questions feel free to reach out!

Sincerely,
harborwater

harborwater changed discussion status to closed Dec 3, 2023

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