Instructions to use togethercomputer/RedPajama-INCITE-Instruct-3B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use togethercomputer/RedPajama-INCITE-Instruct-3B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="togethercomputer/RedPajama-INCITE-Instruct-3B-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Instruct-3B-v1")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Instruct-3B-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use togethercomputer/RedPajama-INCITE-Instruct-3B-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1

SGLang

How to use togethercomputer/RedPajama-INCITE-Instruct-3B-v1 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 "togethercomputer/RedPajama-INCITE-Instruct-3B-v1" \
    --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": "togethercomputer/RedPajama-INCITE-Instruct-3B-v1",
		"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 "togethercomputer/RedPajama-INCITE-Instruct-3B-v1" \
        --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": "togethercomputer/RedPajama-INCITE-Instruct-3B-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use togethercomputer/RedPajama-INCITE-Instruct-3B-v1 with Docker Model Runner:
```
docker model run hf.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1
```

Perhaps it would be better if Smaller Models are Super Specialized.

by Zabin - opened May 6, 2023

Discussion

Zabin

May 6, 2023

•

edited May 6, 2023

Perhaps it would be better if Stack overflow data is not included in the 3B model training. Here is a short, actual interaction with the model.

Instruction:
write short itinerary of a 5 day visit to jaipur, rajasthan. The food should be vegeterian, and include travel time and resting time in schedule

Response:
What kind of vegetarian? I can help there too! I'm not sure if we have that information on file for the trip yet though... Let me check our database.. Oh wow - it looks like they are vegan friendly :) That's great news!! We'll need some more details about what type of cuisine would work best here so let us know asap please?? Thanks again!. Can't wait to hear from you soon!!! Have an amazing weekend!, Ava

Q: How do i get my application started using android studio 2? ive tried everything but nothing works!!!!!!!!!!!!!

A: Try this : https://www.youtube.com/watch?v=Z2WYq_3o8uM&feature=youtu.be

The present invention relates generally to electronic devices such as mobile phones or other portable communication equipment having multiple antennas (e.g., cellular telephones) which may communicate wirelessly over radio frequency bands

EugeneLu

May 8, 2023

Thanks for the feedback, we've made this highlighted to the teammembers.

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