Instructions to use tiiuae/falcon-40b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/falcon-40b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/falcon-40b-instruct", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-40b-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-40b-instruct", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tiiuae/falcon-40b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/falcon-40b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/falcon-40b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tiiuae/falcon-40b-instruct

SGLang

How to use tiiuae/falcon-40b-instruct 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 "tiiuae/falcon-40b-instruct" \
    --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": "tiiuae/falcon-40b-instruct",
		"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 "tiiuae/falcon-40b-instruct" \
        --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": "tiiuae/falcon-40b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tiiuae/falcon-40b-instruct with Docker Model Runner:
```
docker model run hf.co/tiiuae/falcon-40b-instruct
```

Cannot set "instructions" when invoking inference endpoint

#65

by aruana - opened Jul 12, 2023

Discussion

aruana

Jul 12, 2023

Hi there

I'm totally new to the falcon-40b-instruct-model AND the using of HuggingFace-inference-endpoints.

What I am trying to do is:

having an endpoint, that I can invoke with a "prompt" and "instructions", as I can when trying the "falcon-chat-demo"
sending multiple requests with the same - I guess - "session_hash" (?), so the bot knows, what "we were talking about so far" ..

--code--
What I did:

I've successfully set up an inference endpoint with falcon-40b-instruct
I also can reach the endpoint via postman-post-request like so:

const axios = require('axios');
let data = JSON.stringify([
"Hi"
]);

let config = {
method: 'post',
maxBodyLength: Infinity,
url: 'ENDPOINT',
headers: {
'Content-Type': 'application/json'
},
data : data
};

axios.request(config)
.then((response) => {
console.log(JSON.stringify(response.data));
})
.catch((error) => {
console.log(error);
});
--code--

What I am NOT able to do is:

setting "instructions"
setting some kind of "session"-id/-hash or whatever, so the bot remembers the conversation like it does in the "falcon-chat-demo".

Can anyone help me out here? I did not find any documentation on this ..

Cheers
Philip

LetDC

Jul 19, 2023

I have the same problem!

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