Instructions to use quantumaikr/falcon-180B-WizardLM_Orca with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use quantumaikr/falcon-180B-WizardLM_Orca with Transformers:

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

pipe = pipeline("text-generation", model="quantumaikr/falcon-180B-WizardLM_Orca")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("quantumaikr/falcon-180B-WizardLM_Orca")
model = AutoModelForCausalLM.from_pretrained("quantumaikr/falcon-180B-WizardLM_Orca")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use quantumaikr/falcon-180B-WizardLM_Orca with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "quantumaikr/falcon-180B-WizardLM_Orca"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "quantumaikr/falcon-180B-WizardLM_Orca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/quantumaikr/falcon-180B-WizardLM_Orca

SGLang

How to use quantumaikr/falcon-180B-WizardLM_Orca 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 "quantumaikr/falcon-180B-WizardLM_Orca" \
    --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": "quantumaikr/falcon-180B-WizardLM_Orca",
		"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 "quantumaikr/falcon-180B-WizardLM_Orca" \
        --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": "quantumaikr/falcon-180B-WizardLM_Orca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use quantumaikr/falcon-180B-WizardLM_Orca with Docker Model Runner:
```
docker model run hf.co/quantumaikr/falcon-180B-WizardLM_Orca
```

Interesting, What was the dataset inspiration?

by pankajmathur - opened Sep 8, 2023

Discussion

pankajmathur

Sep 8, 2023

Interesting, can't wait to see the evals. May I know, what was the inspiration for the dataset which it was trained on?

quantumaikr

Owner Sep 9, 2023

Thank you for your interest. I chose the "WizardLM_Orca" dataset because I like the combination of WizardLM + Orca, and I think it's a good size and well organized. I didn't get a chance to go through the data. What was your strategy for building the data?

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