Instructions to use davidkim205/Rhea-72b-v0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davidkim205/Rhea-72b-v0.5 with Transformers:

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

pipe = pipeline("text-generation", model="davidkim205/Rhea-72b-v0.5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("davidkim205/Rhea-72b-v0.5")
model = AutoModelForCausalLM.from_pretrained("davidkim205/Rhea-72b-v0.5")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use davidkim205/Rhea-72b-v0.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "davidkim205/Rhea-72b-v0.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davidkim205/Rhea-72b-v0.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/davidkim205/Rhea-72b-v0.5

SGLang

How to use davidkim205/Rhea-72b-v0.5 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 "davidkim205/Rhea-72b-v0.5" \
    --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": "davidkim205/Rhea-72b-v0.5",
		"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 "davidkim205/Rhea-72b-v0.5" \
        --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": "davidkim205/Rhea-72b-v0.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use davidkim205/Rhea-72b-v0.5 with Docker Model Runner:
```
docker model run hf.co/davidkim205/Rhea-72b-v0.5
```

Self-Generated Dataset Creation Method for DPO Learning

by ehartford - opened Mar 25, 2024

Discussion

ehartford

Mar 25, 2024

Would love to check out your methods and data that you discuss on the model card.

Yhyu13

Mar 26, 2024

•

edited Mar 26, 2024

Same here, forgive my ignorance, I couldn't find where SGD was mentioned in the nox framework https://github.com/davidkim205/nox

Also, congrates on ranking #1 on the openllm leaderboard. Looking forward releasing the v1.0 version of Rhea

davidkim205

Owner Mar 27, 2024

I'm sorry. SGD is under research and cannot be made public yet. nox is a framework for sft and dpo.

davidkim205 changed discussion status to closed Apr 3, 2024

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