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 Settings

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
```

How to try Flacon in HuggingChat?

by promptgai - opened May 30, 2023

Discussion

promptgai

May 30, 2023

Steps to try flacon using HuggingChat

MaziyarPanahi

May 31, 2023

If you can change the name of the model_id to tiiuae/falcon-40b-instruct and load it in text-generation-inference you can have it in HuggingChat locally

MaziyarPanahi

Jun 8, 2023

So I successfully managed to use falcon-40b-instruct in text-generation-inference and connect it to HuggingChat. However, I am not sure what should be the following tokens (unlike OpenAssistant):

 "userMessageToken": "<|prompter|>",
 "assistantMessageToken": "<|assistant|>",
 "messageEndToken": "<|endoftext|>",

FalconLLM

Technology Innovation Institute org Jun 9, 2023

We don't have any such tokens set in this instruct version, so you could set the user to "User:", and the assistant to "Assistant:" (if it supports plain text).

TYUIKLJHVHJBN

Jul 13, 2023

Hello, I have falcon-40b-instruct running with text-generation-inference and Huggingchat on a local machine, has anyone else managed to do so? I am not sure of the three tokens listed above and the preprompt, currently the model seems to continue the conversation from the perspective of the user after answering the initial prompt. Any ideas?

MaziyarPanahi

Jul 14, 2023

I am having the same issue with Falcon models in general. The special tokens and how/where they should be used in the various prompts are mostly hit and miss for me and I cannot get this thing to work nicely with external input/context.

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